Загрузка видео...

Не удалось загрузить видео

На главную

🚀Announcing NeRSemble 3D Head Avatar Benchmark v2 Version 2 of the NeRSemble 3D Head Avatar Benchmark systematically evaluates several aspects of 3D head avatar creation. Our goal is to drive progress toward more realistic, robust, and generalizable avatar methods. 🔬Benchmark Tasks The NeRSemble Benchmark v2 features three core challenges:...

MattNiessner's profile picture

Matthias Niessner

49,709 subscribers

30,098 просмотров • 5 месяцев назад •via X (Twitter)

LIVE

Anya Rossi• Live Now

Private livecam show

Комментарии: 0

Нет доступных комментариев

Здесь появятся комментарии из оригинального поста

Похожие видео

Want to create an avatar from a single image? FlexAvatar is a transformer model that creates full 360°, high-quality, and expressive 3D head avatar from just a single portrait image in minutes. Real-time Demo: FlexAvatar's lightweight architecture allows both animation and rendering in real-time, enabling interactive user experiences. To create a new 3D head avatar, only one image is required, e.g., from a webcam. The final avatar is ready after 2 minutes. Architecture: Under the hood, FlexAvatar adopts a transformer-based encoder-decoder design. The encoder maps the input image onto a latent avatar space, while the decoder produces 3D Gaussian attribute maps by incorporating the animation signal via cross-attention. The model learns all facial animations directly from the data without relying on pre-built 3D face models. This equips the avatars with realistic facial expressions. The internal avatar latent space can be conveniently used to integrate additional observations of a person via fitting. This enables use-cases where more than one image of a person is available, e.g., from a phone scan of the person. We train jointly on 2D monocular videos and multi-view data. However, in monocular videos, the animation signal leaks the target viewpoint, causing the model to produce incomplete 3D heads. We call this phenomenon entanglement of driving signal and target viewpoint. To prevent entanglement, we introduce bias sinks. These are learnable tokens that indicate whether a training sample stems from a monocular or a multi-view dataset. During training, the model learns to produce incomplete 3D heads only when the monocular token is present. During inference, FlexAvatar then always uses the multi-view token for which the model has learned to produce complete 3D heads. This simple design allows to combine the generalizability from monocular data with the quality of multi-view data. FlexAvatar summary: - Input: Single-image, phone scan, or monocular video - Output: Full 360° head avatar - Expressive animations - Real-time rendering and animation - Generalization to any portrait - Create a new avatar in 2 minutes - Use bias sinks to combine 2D and 3D data 🏠 🌍 🎥 Great work by Tobias Kirschstein and Simon Giebenhain!
0:30

Want to create an avatar from a single image? FlexAvatar is a transformer model that creates full 360°, high-quality, and expressive 3D head avatar from just a single portrait image in minutes. Real-time Demo: FlexAvatar's lightweight architecture allows both animation and rendering in real-time, enabling interactive user experiences. To create a new 3D head avatar, only one image is required, e.g., from a webcam. The final avatar is ready after 2 minutes. Architecture: Under the hood, FlexAvatar adopts a transformer-based encoder-decoder design. The encoder maps the input image onto a latent avatar space, while the decoder produces 3D Gaussian attribute maps by incorporating the animation signal via cross-attention. The model learns all facial animations directly from the data without relying on pre-built 3D face models. This equips the avatars with realistic facial expressions. The internal avatar latent space can be conveniently used to integrate additional observations of a person via fitting. This enables use-cases where more than one image of a person is available, e.g., from a phone scan of the person. We train jointly on 2D monocular videos and multi-view data. However, in monocular videos, the animation signal leaks the target viewpoint, causing the model to produce incomplete 3D heads. We call this phenomenon entanglement of driving signal and target viewpoint. To prevent entanglement, we introduce bias sinks. These are learnable tokens that indicate whether a training sample stems from a monocular or a multi-view dataset. During training, the model learns to produce incomplete 3D heads only when the monocular token is present. During inference, FlexAvatar then always uses the multi-view token for which the model has learned to produce complete 3D heads. This simple design allows to combine the generalizability from monocular data with the quality of multi-view data. FlexAvatar summary: - Input: Single-image, phone scan, or monocular video - Output: Full 360° head avatar - Expressive animations - Real-time rendering and animation - Generalization to any portrait - Create a new avatar in 2 minutes - Use bias sinks to combine 2D and 3D data 🏠 🌍 🎥 Great work by Tobias Kirschstein and Simon Giebenhain!

Matthias Niessner

96,371 просмотров • 9 месяцев назад

📢Pixel3DMM: Versatile Screen-Space Priors for Single-Image 3D Face Reconstruction📢 -> highly accurate face reconstruction by training powerful VITs via surface normals and UV-coordinates estimation. The geometric cues from our 2D foundation model backbone constrain the 3DMM parameters, which allows us to achieve remarkable reconstruction accuracy - works for both single image and videos! In addition, we introduce a new 3D face reconstruction benchmark that evaluates both neutral and posed face geometry. 🌍 📷 Great work by Simon Giebenhain Tobias Kirschstein Martin Rünz Lourdes Agapito
0:32

📢Pixel3DMM: Versatile Screen-Space Priors for Single-Image 3D Face Reconstruction📢 -> highly accurate face reconstruction by training powerful VITs via surface normals and UV-coordinates estimation. The geometric cues from our 2D foundation model backbone constrain the 3DMM parameters, which allows us to achieve remarkable reconstruction accuracy - works for both single image and videos! In addition, we introduce a new 3D face reconstruction benchmark that evaluates both neutral and posed face geometry. 🌍 📷 Great work by Simon Giebenhain Tobias Kirschstein Martin Rünz Lourdes Agapito

Matthias Niessner

62,462 просмотров • 1 год назад

📢📢 𝐀𝐯𝐚𝐭𝟑𝐫 📢📢 Avat3r creates high-quality 3D head avatars from just a few input images in a single forward pass with a new dynamic 3DGS reconstruction model. Video: Project: Our core idea is to make Gaussian Reconstruction Models animatable. We find that a simple cross-attention to an expression code sequence is already sufficient to model complex facial expressions. We then incorporate position maps from DUSt3R and feature maps from Sapiens to facilitate the prediction task. While DUSt3R's position maps act as a pixel-aligned initialization for the Gaussians' positions, the Sapiens feature maps help the cross-view transformer to match corresponding image tokens in the 4 input images. One major challenge in creating a 3D head avatar from smartphone images comes from inconsistent facial expressions when the subject could not remain perfectly static during the capture. We eliminate this static requirement by simply showing our model input images with different facial expressions during training. This technique makes our model robust to inconsistent input images later on. Finally, we show that despite the model has been trained with 4 input images, one can even create a 3D head avatar when only a single image is available. To achieve this, we employ a pre-trained 3D GAN to lift the single image to 3D and then render the 4 input images for our model. This allows us to create 3D head avatars from single images and even highly out-of-distribution examples like AI generated faces, paintings or statues. Great work by Tobias Kirschstein from his internship at Meta with Javier Romero, Artem Sevastopolsky, and Shunsuke Saito
0:38

📢📢 𝐀𝐯𝐚𝐭𝟑𝐫 📢📢 Avat3r creates high-quality 3D head avatars from just a few input images in a single forward pass with a new dynamic 3DGS reconstruction model. Video: Project: Our core idea is to make Gaussian Reconstruction Models animatable. We find that a simple cross-attention to an expression code sequence is already sufficient to model complex facial expressions. We then incorporate position maps from DUSt3R and feature maps from Sapiens to facilitate the prediction task. While DUSt3R's position maps act as a pixel-aligned initialization for the Gaussians' positions, the Sapiens feature maps help the cross-view transformer to match corresponding image tokens in the 4 input images. One major challenge in creating a 3D head avatar from smartphone images comes from inconsistent facial expressions when the subject could not remain perfectly static during the capture. We eliminate this static requirement by simply showing our model input images with different facial expressions during training. This technique makes our model robust to inconsistent input images later on. Finally, we show that despite the model has been trained with 4 input images, one can even create a 3D head avatar when only a single image is available. To achieve this, we employ a pre-trained 3D GAN to lift the single image to 3D and then render the 4 input images for our model. This allows us to create 3D head avatars from single images and even highly out-of-distribution examples like AI generated faces, paintings or statues. Great work by Tobias Kirschstein from his internship at Meta with Javier Romero, Artem Sevastopolsky, and Shunsuke Saito

Matthias Niessner

74,818 просмотров • 1 год назад

📢📢 𝐏𝐞𝐫𝐜𝐇𝐞𝐚𝐝: 𝐏𝐞𝐫𝐜𝐞𝐩𝐭𝐮𝐚𝐥 𝐇𝐞𝐚𝐝 𝐌𝐨𝐝𝐞𝐥 𝐟𝐨𝐫 𝐒𝐢𝐧𝐠𝐥𝐞-𝐈𝐦𝐚𝐠𝐞 𝟑𝐃 𝐇𝐞𝐚𝐝 𝐑𝐞𝐜𝐨𝐧𝐬𝐭𝐫𝐮𝐜𝐭𝐢𝐨𝐧 & 𝐄𝐝𝐢𝐭𝐢𝐧𝐠📢📢 PercHead reconstructs realistic 3D heads from a single image and enables disentangled 3D editing via geometric controls and style inputs from images or text. At its core is a generalized 3D head decoder trained with perceptual supervision from DINOv2 and SAM 2.1. We find that our new perceptual loss formulation improves reconstruction fidelity compared to commonly-used methods such as LPIPS. Our trained reconstruction model is able to generate 3D-consistent heads from a single input image. Even with challenging side-view inputs, the model robustly infers missing regions for a coherent, high-fidelity output. In addition, our architecture seamlessly adapts to downstream tasks: by swapping the encoder, we can transform the model into a disentangled 3D editing pipeline. In this scenario, we can control geometry through - potentially hand-drawn - segmentation maps, and condition style via image or text prompt. We also provide an interactive GUI to enable the exploration of our editing pipeline. 🌍 📽️ Great work by Antonio Oroz and Tobias Kirschstein
0:30

📢📢 𝐏𝐞𝐫𝐜𝐇𝐞𝐚𝐝: 𝐏𝐞𝐫𝐜𝐞𝐩𝐭𝐮𝐚𝐥 𝐇𝐞𝐚𝐝 𝐌𝐨𝐝𝐞𝐥 𝐟𝐨𝐫 𝐒𝐢𝐧𝐠𝐥𝐞-𝐈𝐦𝐚𝐠𝐞 𝟑𝐃 𝐇𝐞𝐚𝐝 𝐑𝐞𝐜𝐨𝐧𝐬𝐭𝐫𝐮𝐜𝐭𝐢𝐨𝐧 & 𝐄𝐝𝐢𝐭𝐢𝐧𝐠📢📢 PercHead reconstructs realistic 3D heads from a single image and enables disentangled 3D editing via geometric controls and style inputs from images or text. At its core is a generalized 3D head decoder trained with perceptual supervision from DINOv2 and SAM 2.1. We find that our new perceptual loss formulation improves reconstruction fidelity compared to commonly-used methods such as LPIPS. Our trained reconstruction model is able to generate 3D-consistent heads from a single input image. Even with challenging side-view inputs, the model robustly infers missing regions for a coherent, high-fidelity output. In addition, our architecture seamlessly adapts to downstream tasks: by swapping the encoder, we can transform the model into a disentangled 3D editing pipeline. In this scenario, we can control geometry through - potentially hand-drawn - segmentation maps, and condition style via image or text prompt. We also provide an interactive GUI to enable the exploration of our editing pipeline. 🌍 📽️ Great work by Antonio Oroz and Tobias Kirschstein

Matthias Niessner

18,903 просмотров • 10 месяцев назад

I made a digital twin of myself from 10 seconds of video. In the clip: left is the real me, middle is a leading avatar model, right is Mirage Avatar X. Watch the eyes. The difference is not subtle. I have been testing AI avatar models since my first clone in 2023. Every one of them was impressive for about 30 seconds, then your brain caught up. Still eyes. One polite expression. A mouth doing all the work. Avatar X is the first model where that moment never came. Here is what makes it different: It is trained on you. Avatar X preserves your identity. Most avatar models can copy your appearance. Avatar X captures the subtle details that make you you. The way you move, the way you express yourself, and the way you naturally deliver speech. It looks like you. It moves like you. It sounds like you. It understands non-verbal performance Laughing, crying, yawning, sighing. These are the moments where most avatar models fall apart, trying to lip-sync through sounds that aren't words. Avatar X responds naturally, generating realistic facial expressions and micro-expressions instead of forcing every sound into speech. The expression goes beyond the lips Expressions are driven by the audio, through the whole face and body. Ask a question and it furrows its brows and shrugs on the tone. No other model does this to this degree. No quality degradation The first second and the last second look the same. Other models lose quality the longer the video runs. 10 seconds of input That is the entire requirement. Other models need 15 seconds, some even 1 to five minutes. Three years ago my AI clone was a party trick. This one can carry my face, my expressions and my delivery without me in the room. The bar for AI avatars just moved. Avatar X is live today. → Try it here:
0:30

I made a digital twin of myself from 10 seconds of video. In the clip: left is the real me, middle is a leading avatar model, right is Mirage Avatar X. Watch the eyes. The difference is not subtle. I have been testing AI avatar models since my first clone in 2023. Every one of them was impressive for about 30 seconds, then your brain caught up. Still eyes. One polite expression. A mouth doing all the work. Avatar X is the first model where that moment never came. Here is what makes it different: It is trained on you. Avatar X preserves your identity. Most avatar models can copy your appearance. Avatar X captures the subtle details that make you you. The way you move, the way you express yourself, and the way you naturally deliver speech. It looks like you. It moves like you. It sounds like you. It understands non-verbal performance Laughing, crying, yawning, sighing. These are the moments where most avatar models fall apart, trying to lip-sync through sounds that aren't words. Avatar X responds naturally, generating realistic facial expressions and micro-expressions instead of forcing every sound into speech. The expression goes beyond the lips Expressions are driven by the audio, through the whole face and body. Ask a question and it furrows its brows and shrugs on the tone. No other model does this to this degree. No quality degradation The first second and the last second look the same. Other models lose quality the longer the video runs. 10 seconds of input That is the entire requirement. Other models need 15 seconds, some even 1 to five minutes. Three years ago my AI clone was a party trick. This one can carry my face, my expressions and my delivery without me in the room. The bar for AI avatars just moved. Avatar X is live today. → Try it here:

Linus ✦ Ekenstam

20,999 просмотров • 2 месяцев назад

3D-LLM: Injecting the 3D World into Large Language Models paper page: Large language models (LLMs) and Vision-Language Models (VLMs) have been proven to excel at multiple tasks, such as commonsense reasoning. Powerful as these models can be, they are not grounded in the 3D physical world, which involves richer concepts such as spatial relationships, affordances, physics, layout, and so on. In this work, we propose to inject the 3D world into large language models and introduce a whole new family of 3D-LLMs. Specifically, 3D-LLMs can take 3D point clouds and their features as input and perform a diverse set of 3D-related tasks, including captioning, dense captioning, 3D question answering, task decomposition, 3D grounding, 3D-assisted dialog, navigation, and so on. Using three types of prompting mechanisms that we design, we are able to collect over 300k 3D-language data covering these tasks. To efficiently train 3D-LLMs, we first utilize a 3D feature extractor that obtains 3D features from rendered multi- view images. Then, we use 2D VLMs as our backbones to train our 3D-LLMs. By introducing a 3D localization mechanism, 3D-LLMs can better capture 3D spatial information. Experiments on ScanQA show that our model outperforms state-of-the-art baselines by a large margin (e.g., the BLEU-1 score surpasses state-of-the-art score by 9%). Furthermore, experiments on our held-in datasets for 3D captioning, task composition, and 3D-assisted dialogue show that our model outperforms 2D VLMs. Qualitative examples also show that our model could perform more tasks beyond the scope of existing LLMs and VLMs.
0:50

3D-LLM: Injecting the 3D World into Large Language Models paper page: Large language models (LLMs) and Vision-Language Models (VLMs) have been proven to excel at multiple tasks, such as commonsense reasoning. Powerful as these models can be, they are not grounded in the 3D physical world, which involves richer concepts such as spatial relationships, affordances, physics, layout, and so on. In this work, we propose to inject the 3D world into large language models and introduce a whole new family of 3D-LLMs. Specifically, 3D-LLMs can take 3D point clouds and their features as input and perform a diverse set of 3D-related tasks, including captioning, dense captioning, 3D question answering, task decomposition, 3D grounding, 3D-assisted dialog, navigation, and so on. Using three types of prompting mechanisms that we design, we are able to collect over 300k 3D-language data covering these tasks. To efficiently train 3D-LLMs, we first utilize a 3D feature extractor that obtains 3D features from rendered multi- view images. Then, we use 2D VLMs as our backbones to train our 3D-LLMs. By introducing a 3D localization mechanism, 3D-LLMs can better capture 3D spatial information. Experiments on ScanQA show that our model outperforms state-of-the-art baselines by a large margin (e.g., the BLEU-1 score surpasses state-of-the-art score by 9%). Furthermore, experiments on our held-in datasets for 3D captioning, task composition, and 3D-assisted dialogue show that our model outperforms 2D VLMs. Qualitative examples also show that our model could perform more tasks beyond the scope of existing LLMs and VLMs.

AK

249,798 просмотров • 3 лет назад

We’re launching Optima. Now anyone can create a custom benchmark for their use case, leveraging Artificial Analysis’ leading research and platform Building and running benchmarks is difficult. We have distilled Artificial Analysis’ research and experience developing benchmarks into Optima, a new platform for benchmarking models on your own workloads and comparing performance, speed and cost efficiency. Optima allows you to find the best model for your task, or an equally performant alternative to your current setup at 10x lower cost or time per task. We’ve integrated Artificial Analysis' research and experience in benchmarks across the Optima workflow: ➤ Build benchmarks based on your own data and use cases: There are three ways to build a benchmark with Optima. Upload an existing evaluation dataset from your own files or Hugging Face, or import agent traces from platforms including Arize AI, Braintrust and langfuse.com. Install the Optima skill to build a benchmark using context from your coding environment and previous sessions. Or simply describe your use case and provide example inputs and outputs, and Optima will build the benchmark for you ➤ Run across the latest models: Run the same benchmark across leading models in a single click, and keep your leaderboard up to date as soon as new models are released ➤ Bring Artificial Analysis grading to your own benchmark: Evaluate responses against objective rubric criteria or using the same pairwise judging approach used for Artificial Analysis benchmarks including GDPval-AA and AA-Briefcase. For pairwise judging, select your preferred responses from a sample and Optima uses those preferences to rank models across your test set ➤ Compare performance, cost and time efficiency: Optima measures more than model performance. Cost per Task and Time per Task are tracked alongside benchmark scores, with category-level results and support for custom metrics, allowing you to compare the tradeoffs between models for your specific use case Ahead of launch, here are examples questions our beta testers answered with Optima: ➤ Which model can save me 10x the cost without a meaningful decrease in quality for my finance & accounting agent? ➤ Which model best matches the writing style of lawyers for my legal agent? ➤ Which model can best identify different elements in my custom image dataset? Optima is available today. Build your own benchmark at
2:33

We’re launching Optima. Now anyone can create a custom benchmark for their use case, leveraging Artificial Analysis’ leading research and platform Building and running benchmarks is difficult. We have distilled Artificial Analysis’ research and experience developing benchmarks into Optima, a new platform for benchmarking models on your own workloads and comparing performance, speed and cost efficiency. Optima allows you to find the best model for your task, or an equally performant alternative to your current setup at 10x lower cost or time per task. We’ve integrated Artificial Analysis' research and experience in benchmarks across the Optima workflow: ➤ Build benchmarks based on your own data and use cases: There are three ways to build a benchmark with Optima. Upload an existing evaluation dataset from your own files or Hugging Face, or import agent traces from platforms including Arize AI, Braintrust and langfuse.com. Install the Optima skill to build a benchmark using context from your coding environment and previous sessions. Or simply describe your use case and provide example inputs and outputs, and Optima will build the benchmark for you ➤ Run across the latest models: Run the same benchmark across leading models in a single click, and keep your leaderboard up to date as soon as new models are released ➤ Bring Artificial Analysis grading to your own benchmark: Evaluate responses against objective rubric criteria or using the same pairwise judging approach used for Artificial Analysis benchmarks including GDPval-AA and AA-Briefcase. For pairwise judging, select your preferred responses from a sample and Optima uses those preferences to rank models across your test set ➤ Compare performance, cost and time efficiency: Optima measures more than model performance. Cost per Task and Time per Task are tracked alongside benchmark scores, with category-level results and support for custom metrics, allowing you to compare the tradeoffs between models for your specific use case Ahead of launch, here are examples questions our beta testers answered with Optima: ➤ Which model can save me 10x the cost without a meaningful decrease in quality for my finance & accounting agent? ➤ Which model best matches the writing style of lawyers for my legal agent? ➤ Which model can best identify different elements in my custom image dataset? Optima is available today. Build your own benchmark at

Artificial Analysis

133,068 просмотров • 1 месяц назад

Wizstar just hit #1 Product of the Day on Product Hunt, so I had to see what makes its AI avatars different. I tested Wizstar’s digital human technology, and the first thing that stood out was the facial performance. The avatar doesn’t just talk — it can turn its head, move naturally, gesture, and maintain accurate lip sync even when the face or mouth is partially covered by a hand or object. The interesting part is the technology behind it. Wizstar uses a two-stage, audio-driven facial animation system: it first separates speech, mouth movement, and head pose, then reconstructs facial texture and expression details. The result is a much more stable and natural-looking digital human. And you can create a personalized avatar from just a few minutes of source footage, then reuse it for product demos, social content, training, marketing, or localized videos without repeatedly getting in front of a camera. For creators and brands looking to scale video production, this is definitely an AI product worth watching. Congrats to Wizstar_official on reaching #1 Product of the Day on Product Hunt 👀 Try it here: #Wizstar #AIAvatar #ProductHunt #ArtificialIntelligence
0:30

Wizstar just hit #1 Product of the Day on Product Hunt, so I had to see what makes its AI avatars different. I tested Wizstar’s digital human technology, and the first thing that stood out was the facial performance. The avatar doesn’t just talk — it can turn its head, move naturally, gesture, and maintain accurate lip sync even when the face or mouth is partially covered by a hand or object. The interesting part is the technology behind it. Wizstar uses a two-stage, audio-driven facial animation system: it first separates speech, mouth movement, and head pose, then reconstructs facial texture and expression details. The result is a much more stable and natural-looking digital human. And you can create a personalized avatar from just a few minutes of source footage, then reuse it for product demos, social content, training, marketing, or localized videos without repeatedly getting in front of a camera. For creators and brands looking to scale video production, this is definitely an AI product worth watching. Congrats to Wizstar_official on reaching #1 Product of the Day on Product Hunt 👀 Try it here: #Wizstar #AIAvatar #ProductHunt #ArtificialIntelligence

Nas

13,642 просмотров • 1 месяц назад

Today we're announcing microSLAM, a monocular SLAM system built by our computer vision team in Zürich with ETH Zurich's Computer Vision and Geometry Lab. It ranks first on the LaMaria benchmark for monocular SLAM, and holds up against systems that carry many more cameras and IMUs. Ours runs on a single RGB stream. Robot learning is bottlenecked on data, and the largest untapped source is people going about their work. A camera on someone's head for an afternoon in a plant is a record of how that plant actually operates, including all the parts nobody writes down. That data is only useful if you can recover the geometry, and geometry from one moving camera in a world that will not sit still is the hard version of the problem. Solving it monocular is what makes the data cheap. Rigs do not scale to every worker. Glasses do. microSLAM turns that footage into interactive 3D environments where behavioral foundation models can be trained. One person walks a factory floor. A robot learns to navigate it.
3:30

Today we're announcing microSLAM, a monocular SLAM system built by our computer vision team in Zürich with ETH Zurich's Computer Vision and Geometry Lab. It ranks first on the LaMaria benchmark for monocular SLAM, and holds up against systems that carry many more cameras and IMUs. Ours runs on a single RGB stream. Robot learning is bottlenecked on data, and the largest untapped source is people going about their work. A camera on someone's head for an afternoon in a plant is a record of how that plant actually operates, including all the parts nobody writes down. That data is only useful if you can recover the geometry, and geometry from one moving camera in a world that will not sit still is the hard version of the problem. Solving it monocular is what makes the data cheap. Rigs do not scale to every worker. Glasses do. microSLAM turns that footage into interactive 3D environments where behavioral foundation models can be trained. One person walks a factory floor. A robot learns to navigate it.

Gianni Hodel

68,540 просмотров • 18 дней назад

🚀Introducing VisualWebBench: A Comprehensive Benchmark for Multimodal Web Page Understanding and Grounding. 🤔What's this all about? Why this benchmark? > Back in Nov 2023, when we released MMMU ( a comprehensive multimodal understanding benchmark, we received feedback that it included very few UI screenshots. Considering the growing importance of UI understanding, especially with the rise of powerful agents like Devin ( which is built on the strong vision capability of #GPT4, we recognized the need for a benchmark focused on UI screenshot understanding.📸👀 > Multimodal #LLMs have significantly boosted web agents' performance on benchmarks like Mind2Web and WebArena. For instance, the SeeAct agent ( showcases the power of integrating vision into web agents. However, these benchmarks primarily evaluate the end-to-end task execution ability of web agents rather than their understanding of web pages. 🌉 Bridging the Gap with VisualWebBench > To provide a comprehensive evaluation of multimodal LLMs' web page understanding capabilities, we introduce VisualWebBench. Our benchmark spans 139 websites 🌐 across 12 domains 🏷️ and 87 sub-domains 🔍, ensuring a diverse and representative dataset. It assesses MLLMs at three levels: website-level, element-level, and action-level 📊, and encompasses seven tasks designed to evaluate understanding, OCR, grounding, and reasoning abilities 🧠💡. 😮 Surprising Findings > 🎉 Open-source models are catching up: Even though closed-source MLLMs are still leading the leaderboard, we are happy to see open-source models like LLaVA 1.6 34B achieve comparable performance to Gemini Pro. > 🧠 Grounding ability, crucial for developing MLLM-based web applications, is a weakness for most MLLMs. > 🖼️ Importance of Image Resolution: The limited image resolution handling capabilities of most open-source MLLMs restrict their utility in web scenarios, where rich text and elements are prevalent. > 🧱 Relatively strong correlation with general understanding benchmarks like MMMU but weak correlation with web agent benchmarks like Mind2Web. Web agent benchmarks primarily evaluate the end-to-end task execution ability of web agents, which involves a series of actions to accomplish a goal. In contrast, VisualWebBench emphasizes evaluating the foundational skills of MLLMs such as understanding and grounding web page elements. 💡Fun Fact > Claude Sonnet is better than Opus on our benchmark :) 🎓 Conclusion > VisualWebBench serves as a valuable resource for the community, driving research and development in the field of multimodal web page understanding and grounding. As MLLMs continue to evolve and improve, we look forward to seeing new applications and breakthroughs. We believe that our benchmark will contribute to the development of more powerful MLLMs in the web domain, ultimately leading to a more intuitive and efficient user experience on the web. Kudos to the student leads Junpeng Liu Yifan Song and the team Bill Yuchen Lin, Wai Lam, Graham Neubig, Yuanzhi Li! 👏 Check out more details in the Junpeng's thread👇
1:26

🚀Introducing VisualWebBench: A Comprehensive Benchmark for Multimodal Web Page Understanding and Grounding. 🤔What's this all about? Why this benchmark? > Back in Nov 2023, when we released MMMU ( a comprehensive multimodal understanding benchmark, we received feedback that it included very few UI screenshots. Considering the growing importance of UI understanding, especially with the rise of powerful agents like Devin ( which is built on the strong vision capability of #GPT4, we recognized the need for a benchmark focused on UI screenshot understanding.📸👀 > Multimodal #LLMs have significantly boosted web agents' performance on benchmarks like Mind2Web and WebArena. For instance, the SeeAct agent ( showcases the power of integrating vision into web agents. However, these benchmarks primarily evaluate the end-to-end task execution ability of web agents rather than their understanding of web pages. 🌉 Bridging the Gap with VisualWebBench > To provide a comprehensive evaluation of multimodal LLMs' web page understanding capabilities, we introduce VisualWebBench. Our benchmark spans 139 websites 🌐 across 12 domains 🏷️ and 87 sub-domains 🔍, ensuring a diverse and representative dataset. It assesses MLLMs at three levels: website-level, element-level, and action-level 📊, and encompasses seven tasks designed to evaluate understanding, OCR, grounding, and reasoning abilities 🧠💡. 😮 Surprising Findings > 🎉 Open-source models are catching up: Even though closed-source MLLMs are still leading the leaderboard, we are happy to see open-source models like LLaVA 1.6 34B achieve comparable performance to Gemini Pro. > 🧠 Grounding ability, crucial for developing MLLM-based web applications, is a weakness for most MLLMs. > 🖼️ Importance of Image Resolution: The limited image resolution handling capabilities of most open-source MLLMs restrict their utility in web scenarios, where rich text and elements are prevalent. > 🧱 Relatively strong correlation with general understanding benchmarks like MMMU but weak correlation with web agent benchmarks like Mind2Web. Web agent benchmarks primarily evaluate the end-to-end task execution ability of web agents, which involves a series of actions to accomplish a goal. In contrast, VisualWebBench emphasizes evaluating the foundational skills of MLLMs such as understanding and grounding web page elements. 💡Fun Fact > Claude Sonnet is better than Opus on our benchmark :) 🎓 Conclusion > VisualWebBench serves as a valuable resource for the community, driving research and development in the field of multimodal web page understanding and grounding. As MLLMs continue to evolve and improve, we look forward to seeing new applications and breakthroughs. We believe that our benchmark will contribute to the development of more powerful MLLMs in the web domain, ultimately leading to a more intuitive and efficient user experience on the web. Kudos to the student leads Junpeng Liu Yifan Song and the team Bill Yuchen Lin, Wai Lam, Graham Neubig, Yuanzhi Li! 👏 Check out more details in the Junpeng's thread👇

Xiang Yue

56,697 просмотров • 2 лет назад

The day of Parallel Avatars Manifest has come! Sharing some thoughts on them and their place within the Parallel ecosystem… 1. Avatars have immediate utility within the BETA release of the TCG. Matching the Parallel of the Avatar you use to the Parallel of the deck your playing [in ranked matches] will boost $PRIME emissions. Given this, consider if you want one for your favourite Parallel or one for each Parallel to have flexibility in what deck you play. Initial emissions will be set to 11% to ensure all systems are functioning as intended in BETA. 2. Beyond their function in the TCG, Avatars represent a new cornerstone for Parallel as we aspire to more immersive games and story telling. Although we plan to release expansions to the TCG [Planetfall is in development] the Avatars represent our first step towards ‘more ways to play’ and a persistent identity for gamers within the Parallel ecosystem. 3. We are working on finishing full bodies and a migration of Avatars into UE5. This is a process that will take time but ultimately will unlock their potential for use in content and games like Colony. 4. If you obtained an Avatar, you can pay a fee in $PRIME to peak and reveal the door of the Parallel you got but can’t peak to reveal their identity. If you do choose to peak at your avatar, Opensea will reflect this so everyone is aware which Parallel the Avatar belongs to. 5. Although there is varying rarity to the Avatars, there are six hand drawn 1/1 Avatars in the collection. One for each Parallel and one mystery. Special recognition is due to the the team that developed these 3D generated Avatars. It was no small task to develop this program and the detail that has gone into it is unmatched. I am certain it will speak for itself upon reveal. In true Parallel fashion, we stand in a category of our own and bring you something unlike anything the space has seen before. Thank you for your support and may your pulls be Prime. //
0:24

The day of Parallel Avatars Manifest has come! Sharing some thoughts on them and their place within the Parallel ecosystem… 1. Avatars have immediate utility within the BETA release of the TCG. Matching the Parallel of the Avatar you use to the Parallel of the deck your playing [in ranked matches] will boost $PRIME emissions. Given this, consider if you want one for your favourite Parallel or one for each Parallel to have flexibility in what deck you play. Initial emissions will be set to 11% to ensure all systems are functioning as intended in BETA. 2. Beyond their function in the TCG, Avatars represent a new cornerstone for Parallel as we aspire to more immersive games and story telling. Although we plan to release expansions to the TCG [Planetfall is in development] the Avatars represent our first step towards ‘more ways to play’ and a persistent identity for gamers within the Parallel ecosystem. 3. We are working on finishing full bodies and a migration of Avatars into UE5. This is a process that will take time but ultimately will unlock their potential for use in content and games like Colony. 4. If you obtained an Avatar, you can pay a fee in $PRIME to peak and reveal the door of the Parallel you got but can’t peak to reveal their identity. If you do choose to peak at your avatar, Opensea will reflect this so everyone is aware which Parallel the Avatar belongs to. 5. Although there is varying rarity to the Avatars, there are six hand drawn 1/1 Avatars in the collection. One for each Parallel and one mystery. Special recognition is due to the the team that developed these 3D generated Avatars. It was no small task to develop this program and the detail that has gone into it is unmatched. I am certain it will speak for itself upon reveal. In true Parallel fashion, we stand in a category of our own and bring you something unlike anything the space has seen before. Thank you for your support and may your pulls be Prime. //

//Kalos

25,589 просмотров • 3 лет назад

Most AI avatars still struggle with the same problems: lip-sync breaks during head turns, faces become unstable when partially covered, and movements often feel robotic. After looking into Wizstar's approach, the technical side is what stands out. Instead of directly generating facial motion from audio, Wizstar uses a two-stage, audio-driven animation pipeline: • Separates speech, mouth motion, and head pose into independent signals • Reconstructs facial textures and expressions afterward for greater realism and stability That architecture helps maintain accurate lip-sync even when the mouth is partially obscured, the camera angle changes dramatically, or the speaker makes fast movements. What impressed me most is that the avatars don't just talk—they gesture, interact with objects, and move more like real presenters than traditional AI avatars. And it’s not just the tech that caught attention—Wizstar has now claimed the #1 spot among Product Hunt’s Top Products. 🏆 🧵 For creators and businesses, the bigger advantage is scale: → Create a digital avatar once → Generate multilingual content in 75+ languages → Produce localized videos without filming, reshoots, or studio setups Marketing videos, product demos, training content, sales outreach, global campaigns—everything becomes significantly faster to produce. Definitely one of the more interesting AI avatar systems I've seen recently. Try it here: Wizstar_official #Wizstar
0:24

Most AI avatars still struggle with the same problems: lip-sync breaks during head turns, faces become unstable when partially covered, and movements often feel robotic. After looking into Wizstar's approach, the technical side is what stands out. Instead of directly generating facial motion from audio, Wizstar uses a two-stage, audio-driven animation pipeline: • Separates speech, mouth motion, and head pose into independent signals • Reconstructs facial textures and expressions afterward for greater realism and stability That architecture helps maintain accurate lip-sync even when the mouth is partially obscured, the camera angle changes dramatically, or the speaker makes fast movements. What impressed me most is that the avatars don't just talk—they gesture, interact with objects, and move more like real presenters than traditional AI avatars. And it’s not just the tech that caught attention—Wizstar has now claimed the #1 spot among Product Hunt’s Top Products. 🏆 🧵 For creators and businesses, the bigger advantage is scale: → Create a digital avatar once → Generate multilingual content in 75+ languages → Produce localized videos without filming, reshoots, or studio setups Marketing videos, product demos, training content, sales outreach, global campaigns—everything becomes significantly faster to produce. Definitely one of the more interesting AI avatar systems I've seen recently. Try it here: Wizstar_official #Wizstar

ɱҽԃι✨

49,060 просмотров • 1 месяц назад

🚀 Announcing Echo — our new frontier model for 3D world generation. Echo turns a simple text prompt or image into a fully explorable, 3D-consistent world. Instead of disconnected views, the result is a single, coherent spatial representation you can move through freely. This is part of a bigger shift in AI: from generating pixels and tokens to generating spaces. Echo predicts a geometry-grounded 3D scene at metric scale, meaning every novel view, depth map, and interaction comes from the same underlying world — not independent hallucinations. Once generated, the world is interactive in real time. You control the camera, explore from any angle, and render instantly — even on low-end hardware, directly in the browser. High-quality 3D world exploration is no longer gated by expensive equipment. Under the hood, Echo infers a physically grounded 3D representation and converts it into a renderable format. For our web demo, we use 3D Gaussian Splatting (3DGS) for fast, GPU-friendly rendering — but the representation itself is flexible and can be easily adapted. Why this matters: consistent 3D worlds unlock real workflows — digital twins, 3D design, game environments, robotics simulation, and more. From a single photo or a line of text, Echo builds worlds that are reliable, editable, and spatially faithful. Echo also enables scene editing and restyling. Change materials, remove or add objects, explore design variations — all while preserving global 3D consistency. Editing no longer breaks the world. This is only the beginning. Echo is the foundation for future world models with dynamics, physical reasoning, and richer interaction — environments that don’t just look right, but behave right. Explore the generated worlds on our website and sign up for the closed beta. The era of spatial intelligence starts here. 🌍 #Echo #WorldModels #SpatialAI #3DFoundationModels Check it out:
1:07

🚀 Announcing Echo — our new frontier model for 3D world generation. Echo turns a simple text prompt or image into a fully explorable, 3D-consistent world. Instead of disconnected views, the result is a single, coherent spatial representation you can move through freely. This is part of a bigger shift in AI: from generating pixels and tokens to generating spaces. Echo predicts a geometry-grounded 3D scene at metric scale, meaning every novel view, depth map, and interaction comes from the same underlying world — not independent hallucinations. Once generated, the world is interactive in real time. You control the camera, explore from any angle, and render instantly — even on low-end hardware, directly in the browser. High-quality 3D world exploration is no longer gated by expensive equipment. Under the hood, Echo infers a physically grounded 3D representation and converts it into a renderable format. For our web demo, we use 3D Gaussian Splatting (3DGS) for fast, GPU-friendly rendering — but the representation itself is flexible and can be easily adapted. Why this matters: consistent 3D worlds unlock real workflows — digital twins, 3D design, game environments, robotics simulation, and more. From a single photo or a line of text, Echo builds worlds that are reliable, editable, and spatially faithful. Echo also enables scene editing and restyling. Change materials, remove or add objects, explore design variations — all while preserving global 3D consistency. Editing no longer breaks the world. This is only the beginning. Echo is the foundation for future world models with dynamics, physical reasoning, and richer interaction — environments that don’t just look right, but behave right. Explore the generated worlds on our website and sign up for the closed beta. The era of spatial intelligence starts here. 🌍 #Echo #WorldModels #SpatialAI #3DFoundationModels Check it out:

SpAItial AI

177,073 просмотров • 9 месяцев назад

🚀AI NEXUS 2.0 - A NEW ERA BEGINS Happy One Year Anniversary! During the bear… we proved the model: • Over 350K installs of the AI Nexus Mobile App • 150K wallets onboarded to Multiversᕽ • Turning people’s socials → playable 3D avatars in minutes • 60+ partner projects onboarded to our ecosystem But it's not enough. Now, we upgrade... Welcome to AI Nexus 2.0 AI Nexus 2.0 = AI + Gaming Infrastructure. Powered by $A1X. Cross-chain. Creator-driven. Identity-first. Built for everyone: from everyday mobile users to full game studios. AI Nexus becomes a superlayer for digital identity, gaming and AI-powered creation. And over the coming weeks (before end of the year), we’ll reveal every part of it in clear, bite-sized drops. What’s Coming in AI Nexus 2.0? 1. Two brand-new apps (launching sooner than you think!). 2. Deeper strategic, revenue-driven integrations with Ice Open Network, Multiversᕽ, , Linera ⛓️ & more. 3. Marketplace for Avatars / Assets; powered by NFTs. 4. SDK for effortless 3D avatar creation. 5. $A1X total supply reduction. 6. More AI tools coming to AI Nexus Mobile App & games to the Clone Machine. 7. New staking + developer incentive programs. AI Nexus 2.0 is bigger, broader, and built to scale. And we’re just getting started.
0:38

🚀AI NEXUS 2.0 - A NEW ERA BEGINS Happy One Year Anniversary! During the bear… we proved the model: • Over 350K installs of the AI Nexus Mobile App • 150K wallets onboarded to Multiversᕽ • Turning people’s socials → playable 3D avatars in minutes • 60+ partner projects onboarded to our ecosystem But it's not enough. Now, we upgrade... Welcome to AI Nexus 2.0 AI Nexus 2.0 = AI + Gaming Infrastructure. Powered by $A1X. Cross-chain. Creator-driven. Identity-first. Built for everyone: from everyday mobile users to full game studios. AI Nexus becomes a superlayer for digital identity, gaming and AI-powered creation. And over the coming weeks (before end of the year), we’ll reveal every part of it in clear, bite-sized drops. What’s Coming in AI Nexus 2.0? 1. Two brand-new apps (launching sooner than you think!). 2. Deeper strategic, revenue-driven integrations with Ice Open Network, Multiversᕽ, , Linera ⛓️ & more. 3. Marketplace for Avatars / Assets; powered by NFTs. 4. SDK for effortless 3D avatar creation. 5. $A1X total supply reduction. 6. More AI tools coming to AI Nexus Mobile App & games to the Clone Machine. 7. New staking + developer incentive programs. AI Nexus 2.0 is bigger, broader, and built to scale. And we’re just getting started.

AI Nexus

172,611 просмотров • 9 месяцев назад

great to see more people generating 3d avatars with our new text-to-3d feature in forge. this marks a step in the right direction in putting powerful creation tools directly in the hands of everyone. we built forge entirely from the ground up over the past months as one of the key releases on our roadmap. having full proprietary ownership of the technology gives us complete control to shape its direction without depending on external platforms or third-party licenses. building on this foundation, our upcoming studio feature will let users generate high-quality accessories, clothing, and environments simply by typing natural language prompts. a single description can produce fully textured, production-ready 3d assets in seconds, with options to create multiple variations and refine them through follow-up instructions.every asset created in studio integrates seamlessly with the 3d ai agents made in forge on users can instantly apply clothing and accessories with automatic fitting, layer multiple items, and place their agents inside custom-generated environments. all clothing and accessories come pre-rigged and optimized, while environments include proper lighting and geometry for immediate use in games, animation, virtual worlds, and more. we have spent months thoughtfully designing how can deliver real, sustainable value back to the community. we will continue to share more details on token utility use cases and the economic flywheel we have built. the goal is to create a self-reinforcing system where creators earn through royalties, autonomous agents drive on-chain activity, and platform growth directly benefits active community members and token holders. together, these features enable a complete creative flow. from a simple idea, anyone can quickly build fully realized 3d ai agents standing in rich, custom scenes. we are excited to see what the community builds next.
0:24

great to see more people generating 3d avatars with our new text-to-3d feature in forge. this marks a step in the right direction in putting powerful creation tools directly in the hands of everyone. we built forge entirely from the ground up over the past months as one of the key releases on our roadmap. having full proprietary ownership of the technology gives us complete control to shape its direction without depending on external platforms or third-party licenses. building on this foundation, our upcoming studio feature will let users generate high-quality accessories, clothing, and environments simply by typing natural language prompts. a single description can produce fully textured, production-ready 3d assets in seconds, with options to create multiple variations and refine them through follow-up instructions.every asset created in studio integrates seamlessly with the 3d ai agents made in forge on users can instantly apply clothing and accessories with automatic fitting, layer multiple items, and place their agents inside custom-generated environments. all clothing and accessories come pre-rigged and optimized, while environments include proper lighting and geometry for immediate use in games, animation, virtual worlds, and more. we have spent months thoughtfully designing how can deliver real, sustainable value back to the community. we will continue to share more details on token utility use cases and the economic flywheel we have built. the goal is to create a self-reinforcing system where creators earn through royalties, autonomous agents drive on-chain activity, and platform growth directly benefits active community members and token holders. together, these features enable a complete creative flow. from a simple idea, anyone can quickly build fully realized 3d ai agents standing in rich, custom scenes. we are excited to see what the community builds next.

nich

19,611 просмотров • 3 месяцев назад

Multi-Track Timeline Control for Text-Driven 3D Human Motion Generation paper page: Recent advances in generative modeling have led to promising progress on synthesizing 3D human motion from text, with methods that can generate character animations from short prompts and specified durations. However, using a single text prompt as input lacks the fine-grained control needed by animators, such as composing multiple actions and defining precise durations for parts of the motion. To address this, we introduce the new problem of timeline control for text-driven motion synthesis, which provides an intuitive, yet fine-grained, input interface for users. Instead of a single prompt, users can specify a multi-track timeline of multiple prompts organized in temporal intervals that may overlap. This enables specifying the exact timings of each action and composing multiple actions in sequence or at overlapping intervals. To generate composite animations from a multi-track timeline, we propose a new test-time denoising method. This method can be integrated with any pre-trained motion diffusion model to synthesize realistic motions that accurately reflect the timeline. At every step of denoising, our method processes each timeline interval (text prompt) individually, subsequently aggregating the predictions with consideration for the specific body parts engaged in each action. Experimental comparisons and ablations validate that our method produces realistic motions that respect the semantics and timing of given text prompts.
0:21

Multi-Track Timeline Control for Text-Driven 3D Human Motion Generation paper page: Recent advances in generative modeling have led to promising progress on synthesizing 3D human motion from text, with methods that can generate character animations from short prompts and specified durations. However, using a single text prompt as input lacks the fine-grained control needed by animators, such as composing multiple actions and defining precise durations for parts of the motion. To address this, we introduce the new problem of timeline control for text-driven motion synthesis, which provides an intuitive, yet fine-grained, input interface for users. Instead of a single prompt, users can specify a multi-track timeline of multiple prompts organized in temporal intervals that may overlap. This enables specifying the exact timings of each action and composing multiple actions in sequence or at overlapping intervals. To generate composite animations from a multi-track timeline, we propose a new test-time denoising method. This method can be integrated with any pre-trained motion diffusion model to synthesize realistic motions that accurately reflect the timeline. At every step of denoising, our method processes each timeline interval (text prompt) individually, subsequently aggregating the predictions with consideration for the specific body parts engaged in each action. Experimental comparisons and ablations validate that our method produces realistic motions that respect the semantics and timing of given text prompts.

AK

126,635 просмотров • 2 лет назад

Wow. Recreating the Shawshank Redemption prison in 3D from a single video, in real time (!) Just read the MASt3R-SLAM paper and it's pretty neat. These folks basically built a real-time dense SLAM system on top of MASt3R, which is a transformer-based neural network that can do 3d reconstruction and localization from uncalibrated image pairs. The cool part is they don't need a fixed camera model -- it just works with arbitrary cameras -- think different focal lengths, sensor sizes, even handling zooming in video (FMV drone video anyone?!). If you've done photogrammetry or played with NeRFs you know that is a HUGE deal. They've solved some tricky problems like efficient point matching and tracking, plus they've figured out how to fuse point clouds and handle loop closures in real-time. Their system runs at about 15 FPS on a 4090 and produces both camera poses and dense geometry. When they know the camera calibration, they get SOTA results across several benchmarks, but even without calibration, they still perform well. What's interesting is the approach -- most recent SLAM work has built on DROID-SLAM's architecture, but these folks went a different direction by leveraging a strong 3D reconstruction prior. Seems to give them more coherent geometry, which makes sense since that's what MASt3R was designed for. For anyone who cares about monocular SLAM and 3D reconstruction, this feels like a significant step toward plug-and-play dense SLAM without calibration headaches -- perfect for drones, robots, AR/VR -- the works!
0:29

Wow. Recreating the Shawshank Redemption prison in 3D from a single video, in real time (!) Just read the MASt3R-SLAM paper and it's pretty neat. These folks basically built a real-time dense SLAM system on top of MASt3R, which is a transformer-based neural network that can do 3d reconstruction and localization from uncalibrated image pairs. The cool part is they don't need a fixed camera model -- it just works with arbitrary cameras -- think different focal lengths, sensor sizes, even handling zooming in video (FMV drone video anyone?!). If you've done photogrammetry or played with NeRFs you know that is a HUGE deal. They've solved some tricky problems like efficient point matching and tracking, plus they've figured out how to fuse point clouds and handle loop closures in real-time. Their system runs at about 15 FPS on a 4090 and produces both camera poses and dense geometry. When they know the camera calibration, they get SOTA results across several benchmarks, but even without calibration, they still perform well. What's interesting is the approach -- most recent SLAM work has built on DROID-SLAM's architecture, but these folks went a different direction by leveraging a strong 3D reconstruction prior. Seems to give them more coherent geometry, which makes sense since that's what MASt3R was designed for. For anyone who cares about monocular SLAM and 3D reconstruction, this feels like a significant step toward plug-and-play dense SLAM without calibration headaches -- perfect for drones, robots, AR/VR -- the works!

Bilawal Sidhu

704,366 просмотров • 1 год назад

🚀 The Segment Anything Model (SAM) has been upgraded to SAM2, featuring an efficient image encoder for segmenting images and videos. But does SAM2 outperform SAM1 in medical image and video segmentation? We're thrilled to present our paper "Segment Anything in Medical Images and Videos: Benchmark and Deployment"! We comprehensively benchmark SAM2 across 11 medical image modalities and videos. 📄 Paper: 💻 Code: **Highlights:** 1. SAM2 doesn’t always outperform SAM1 in 2D medical images, but excels in video segmentation, making it more accurate and efficient for 3D images, such as CT and MR scans. 2. MedSAM still outperforms SAM2 on most 2D modalities, but SAM2 surpasses MedSAM for 3D image segmentation in a slice-by-slice approach. 3. Segmentation performance varies with model size; sometimes the smallest model outperforms larger ones. 4. Fine-tuning SAM2 significantly boosts its performance for medical image segmentation. While SAM2 may struggle with challenging objects that have unclear boundaries or low contrast, it excels in generating good initial segmentation masks for common medical images and videos. However, the official interface doesn’t support medical data formats and has limitations on video length. To address this, we've developed a 3D Slicer Plugin and Gradio API for efficient 3D medical image and video segmentation. We invite you to try them out and provide feedback! 🔧 Deployment: - 3D Slicer Plugin: - Gradio API: (Note: Due to GPU limitations, the online API is available for only 12 hours and may be slow. We highly recommend deploying the Gradio API with your own computing resources: A big shoutout to Jun Ma (JunMa) who recently joined our UHN AI hub (UHN AI Hub) as Machine Learning Lead, and kudos to all co-authors: Sumin Kim, Feifei Li, Mohammed Baharoon (Mohammed Baharoon), Reza Asakereh, and Hongwei Lyu! This is true teamwork! Looking forward to collaborating with the community to advance 3D medical image and video segmentation foundation models! University Health Network U of T Department of Computer Science Department of Laboratory Medicine & Pathobiology Temerty Centre for AI in Medicine (T-CAIREM) Vector Institute #MedTech #AIinHealthcare #DeepLearning #MedicalImaging #SAM2 #MedSAM #AIResearch
0:22

🚀 The Segment Anything Model (SAM) has been upgraded to SAM2, featuring an efficient image encoder for segmenting images and videos. But does SAM2 outperform SAM1 in medical image and video segmentation? We're thrilled to present our paper "Segment Anything in Medical Images and Videos: Benchmark and Deployment"! We comprehensively benchmark SAM2 across 11 medical image modalities and videos. 📄 Paper: 💻 Code: **Highlights:** 1. SAM2 doesn’t always outperform SAM1 in 2D medical images, but excels in video segmentation, making it more accurate and efficient for 3D images, such as CT and MR scans. 2. MedSAM still outperforms SAM2 on most 2D modalities, but SAM2 surpasses MedSAM for 3D image segmentation in a slice-by-slice approach. 3. Segmentation performance varies with model size; sometimes the smallest model outperforms larger ones. 4. Fine-tuning SAM2 significantly boosts its performance for medical image segmentation. While SAM2 may struggle with challenging objects that have unclear boundaries or low contrast, it excels in generating good initial segmentation masks for common medical images and videos. However, the official interface doesn’t support medical data formats and has limitations on video length. To address this, we've developed a 3D Slicer Plugin and Gradio API for efficient 3D medical image and video segmentation. We invite you to try them out and provide feedback! 🔧 Deployment: - 3D Slicer Plugin: - Gradio API: (Note: Due to GPU limitations, the online API is available for only 12 hours and may be slow. We highly recommend deploying the Gradio API with your own computing resources: A big shoutout to Jun Ma (JunMa) who recently joined our UHN AI hub (UHN AI Hub) as Machine Learning Lead, and kudos to all co-authors: Sumin Kim, Feifei Li, Mohammed Baharoon (Mohammed Baharoon), Reza Asakereh, and Hongwei Lyu! This is true teamwork! Looking forward to collaborating with the community to advance 3D medical image and video segmentation foundation models! University Health Network U of T Department of Computer Science Department of Laboratory Medicine & Pathobiology Temerty Centre for AI in Medicine (T-CAIREM) Vector Institute #MedTech #AIinHealthcare #DeepLearning #MedicalImaging #SAM2 #MedSAM #AIResearch

Bo Wang

178,710 просмотров • 2 лет назад

BMW's upcoming all-electric iX3 SUV: • Expected EPA range: Over 400 miles (according to BMW) • Up to 400kW charging speeds. Can add ~200 miles of range in 10 mins • New “superbrain” will provide 20X the computing power of BMW’s previous system • Redesigned cockpit: Panoramic display shows information from A-pillar to A-pillar, 3D Head-Up, central display with matrix LEDs • Uses 2,000 feet less wiring than before • 800-volt • Bidirectional charging functions: Vehicle-to-Home (V2H) and Vehicle-to-Grid (V2G) • 20% lower drag coefficient • BMW: "BMW Group’s latest driver assistance systems are among the world’s best. the iX3 merges the proven, rule-based assistance system with a new system based on AI. In an optimum symbiosis, this combination supports the driver even more precisely and reliably in challenging situations on the road. The Superbrain of Automated Driving pools all customer functions for automated driving and has a 20x faster processing speed than the previous system." • Production version of the iX3 will be unveiled in Munich next month (Sept). Will go on sale in the US in Q2 2026. • Expected starting price: Between $55k-$60k. BMW CEO on the new iX3: “This will be the benchmark of the industry. BMW can build superior electric cars, and the rest of the market will have to answer.”
0:39

BMW's upcoming all-electric iX3 SUV: • Expected EPA range: Over 400 miles (according to BMW) • Up to 400kW charging speeds. Can add ~200 miles of range in 10 mins • New “superbrain” will provide 20X the computing power of BMW’s previous system • Redesigned cockpit: Panoramic display shows information from A-pillar to A-pillar, 3D Head-Up, central display with matrix LEDs • Uses 2,000 feet less wiring than before • 800-volt • Bidirectional charging functions: Vehicle-to-Home (V2H) and Vehicle-to-Grid (V2G) • 20% lower drag coefficient • BMW: "BMW Group’s latest driver assistance systems are among the world’s best. the iX3 merges the proven, rule-based assistance system with a new system based on AI. In an optimum symbiosis, this combination supports the driver even more precisely and reliably in challenging situations on the road. The Superbrain of Automated Driving pools all customer functions for automated driving and has a 20x faster processing speed than the previous system." • Production version of the iX3 will be unveiled in Munich next month (Sept). Will go on sale in the US in Q2 2026. • Expected starting price: Between $55k-$60k. BMW CEO on the new iX3: “This will be the benchmark of the industry. BMW can build superior electric cars, and the rest of the market will have to answer.”

Sawyer Merritt

45,945 просмотров • 1 год назад

We’re thrilled to share that our MERFISH+ preprint is now live on bioRxiv!👉 In this work, the Bintu and Zhu labs (UCSD) developed MERFISH+, a next-generation spatial genomics platform that combines genome-wide RNA and epigenetic imaging over a large field of view. By introducing acrydite-modified probes covalently anchored to hydrogels, MERFISH+ achieves remarkable imaging stability and enables >1,800-gene, multi-modal, and multi-month experiments. With this platform, they, together with the Chi lab at UCSD, profiled a whole developing human heart at 12 post-conception week with merely two slides, resulting in a total of 53 slides, 3.1 million single cells and more than 30 cell types. Building upon our previous 3D reconstruction and modeling framework, Spateo ( we reconstruct the 3D human heart that nicely captures the anatomical structure of the heart, including the intricate vasculature network. Sophisticated analyses provide a holistic view of an entire organ and enable systematic characterization of 3D cellular neighborhoods and transcriptional gradients of substructures such as the descending arteries. Furthermore, using a generative integration framework for spatial multimodal data (Spateo-VI), we harmonized these MERFISH+ transcriptomic and chromatin data to reconstruct a 3D spatially-resolved multi-omics atlas of the developing human heart, shared at and MERFISH+ thus sets a new standard for large-format, multi-omic spatial profiling, enabling holistic, 3D characterization of organs at subcellular resolution. Huge congratulations to first authors Colin Kern, qingquan Zhang, Yifan Lu , and Jacqueline Eschbach, and to all collaborators from the Bintu, Zhu, Chi, and Qiu labs for this amazing team effort. Thanks for your diligence, creativity, and hard work on this project. We’re grateful for support from Arc Institute and our generous donors. Our lab is expanding—if you’re excited about building the next generation of single-cell and spatial genomics techniques and predictive single cell and spatial foundation models, we’re hiring! If you are interested, please reach out to me via direct message or email at xiaojie@stanford.edu. We are excited for any potential collaborations along this line of research in Stanford, UCSF and Berkeley and other labs as well.
0:42

We’re thrilled to share that our MERFISH+ preprint is now live on bioRxiv!👉 In this work, the Bintu and Zhu labs (UCSD) developed MERFISH+, a next-generation spatial genomics platform that combines genome-wide RNA and epigenetic imaging over a large field of view. By introducing acrydite-modified probes covalently anchored to hydrogels, MERFISH+ achieves remarkable imaging stability and enables >1,800-gene, multi-modal, and multi-month experiments. With this platform, they, together with the Chi lab at UCSD, profiled a whole developing human heart at 12 post-conception week with merely two slides, resulting in a total of 53 slides, 3.1 million single cells and more than 30 cell types. Building upon our previous 3D reconstruction and modeling framework, Spateo ( we reconstruct the 3D human heart that nicely captures the anatomical structure of the heart, including the intricate vasculature network. Sophisticated analyses provide a holistic view of an entire organ and enable systematic characterization of 3D cellular neighborhoods and transcriptional gradients of substructures such as the descending arteries. Furthermore, using a generative integration framework for spatial multimodal data (Spateo-VI), we harmonized these MERFISH+ transcriptomic and chromatin data to reconstruct a 3D spatially-resolved multi-omics atlas of the developing human heart, shared at and MERFISH+ thus sets a new standard for large-format, multi-omic spatial profiling, enabling holistic, 3D characterization of organs at subcellular resolution. Huge congratulations to first authors Colin Kern, qingquan Zhang, Yifan Lu , and Jacqueline Eschbach, and to all collaborators from the Bintu, Zhu, Chi, and Qiu labs for this amazing team effort. Thanks for your diligence, creativity, and hard work on this project. We’re grateful for support from Arc Institute and our generous donors. Our lab is expanding—if you’re excited about building the next generation of single-cell and spatial genomics techniques and predictive single cell and spatial foundation models, we’re hiring! If you are interested, please reach out to me via direct message or email at [email protected]. We are excited for any potential collaborations along this line of research in Stanford, UCSF and Berkeley and other labs as well.

evo-devo

42,340 просмотров • 10 месяцев назад