正在加载视频...

视频加载失败

加载此视频时出现问题。这可能是由于临时网络问题，或视频可能不可用。

#CVPR2026 Can frontier LLMs write PhD-level 3D vision code? We introduce GeoCodeBench, a benchmark that asks models to read real 3D geometric vision papers and implement core functions. Best result so far: GPT-5 reaches only 36.6%. This suggests that scientific coding in 3D vision remains far from solved. Paper: Project:

Hao Zhao

1,130 subscribers

18,164 次观看 • 2 个月前 •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

0 条评论

暂无评论

原始帖子的评论将显示在这里

相关视频

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.

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

249,708 次观看 • 3 年前

LLaVA-3D A Simple yet Effective Pathway to Empowering LMMs with 3D-awareness Recent advancements in Large Multimodal Models (LMMs) have greatly enhanced their proficiency in 2D visual understanding tasks, enabling them to effectively process and understand images and videos. However, the development of LMMs with 3D-awareness for 3D scene understanding has been hindered by the lack of large-scale 3D vision-language datasets and powerful 3D encoders. In this paper, we introduce a simple yet effective framework called LLaVA-3D. Leveraging the strong 2D understanding priors from LLaVA, our LLaVA-3D efficiently adapts LLaVA for 3D scene understanding without compromising 2D understanding capabilities. To achieve this, we employ a simple yet effective representation, 3D Patch, which connects 2D CLIP patch features with their corresponding positions in 3D space. By integrating the 3D Patches into 2D LMMs and employing joint 2D and 3D vision-language instruction tuning, we establish a unified architecture for both 2D image understanding and 3D scene understanding. Experimental results show that LLaVA-3D converges 3.5x faster than existing 3D LMMs when trained on 3D vision-language datasets. Moreover, LLaVA-3D not only achieves state-of-the-art performance across various 3D tasks but also maintains comparable 2D image understanding and vision-language conversation capabilities with LLaVA.

LLaVA-3D A Simple yet Effective Pathway to Empowering LMMs with 3D-awareness Recent advancements in Large Multimodal Models (LMMs) have greatly enhanced their proficiency in 2D visual understanding tasks, enabling them to effectively process and understand images and videos. However, the development of LMMs with 3D-awareness for 3D scene understanding has been hindered by the lack of large-scale 3D vision-language datasets and powerful 3D encoders. In this paper, we introduce a simple yet effective framework called LLaVA-3D. Leveraging the strong 2D understanding priors from LLaVA, our LLaVA-3D efficiently adapts LLaVA for 3D scene understanding without compromising 2D understanding capabilities. To achieve this, we employ a simple yet effective representation, 3D Patch, which connects 2D CLIP patch features with their corresponding positions in 3D space. By integrating the 3D Patches into 2D LMMs and employing joint 2D and 3D vision-language instruction tuning, we establish a unified architecture for both 2D image understanding and 3D scene understanding. Experimental results show that LLaVA-3D converges 3.5x faster than existing 3D LMMs when trained on 3D vision-language datasets. Moreover, LLaVA-3D not only achieves state-of-the-art performance across various 3D tasks but also maintains comparable 2D image understanding and vision-language conversation capabilities with LLaVA.

AK

41,736 次观看 • 1 年前

DL3DV-10K: A Large-Scale Scene Dataset for Deep Learning-based 3D Vision paper page: We have witnessed significant progress in deep learning-based 3D vision, ranging from neural radiance field (NeRF) based 3D representation learning to applications in novel view synthesis (NVS). However, existing scene-level datasets for deep learning-based 3D vision, limited to either synthetic environments or a narrow selection of real-world scenes, are quite insufficient. This insufficiency not only hinders a comprehensive benchmark of existing methods but also caps what could be explored in deep learning-based 3D analysis. To address this critical gap, we present DL3DV-10K, a large-scale scene dataset, featuring 51.2 million frames from 10,510 videos captured from 65 types of point-of-interest (POI) locations, covering both bounded and unbounded scenes, with different levels of reflection, transparency, and lighting. We conducted a comprehensive benchmark of recent NVS methods on DL3DV-10K, which revealed valuable insights for future research in NVS. In addition, we have obtained encouraging results in a pilot study to learn generalizable NeRF from DL3DV-10K, which manifests the necessity of a large-scale scene-level dataset to forge a path toward a foundation model for learning 3D representation.

DL3DV-10K: A Large-Scale Scene Dataset for Deep Learning-based 3D Vision paper page: We have witnessed significant progress in deep learning-based 3D vision, ranging from neural radiance field (NeRF) based 3D representation learning to applications in novel view synthesis (NVS). However, existing scene-level datasets for deep learning-based 3D vision, limited to either synthetic environments or a narrow selection of real-world scenes, are quite insufficient. This insufficiency not only hinders a comprehensive benchmark of existing methods but also caps what could be explored in deep learning-based 3D analysis. To address this critical gap, we present DL3DV-10K, a large-scale scene dataset, featuring 51.2 million frames from 10,510 videos captured from 65 types of point-of-interest (POI) locations, covering both bounded and unbounded scenes, with different levels of reflection, transparency, and lighting. We conducted a comprehensive benchmark of recent NVS methods on DL3DV-10K, which revealed valuable insights for future research in NVS. In addition, we have obtained encouraging results in a pilot study to learn generalizable NeRF from DL3DV-10K, which manifests the necessity of a large-scale scene-level dataset to forge a path toward a foundation model for learning 3D representation.

AK

49,920 次观看 • 2 年前

They finally did it! YouTube is now an official app for Apple Vision Pro and can be downloaded from the App Store. It features 3D, 180 and 360-degree content and an optimised user interface. So far I really like it. Still, it feels surreal that this is actually happening.

They finally did it! YouTube is now an official app for Apple Vision Pro and can be downloaded from the App Store. It features 3D, 180 and 360-degree content and an optimised user interface. So far I really like it. Still, it feels surreal that this is actually happening.

Phil Traut ᯅ

74,900 次观看 • 5 个月前

Humans draw to facilitate reasoning and communication. Why not let LLMs do so? 🚀We introduce✏️Sketchpad, which gives multimodal LLMs a sketchpad to draw and facilitate reasoning! Sketchpad gives GPT-4o great boosts on many vision and math tasks 📈 The video shows how GPT-4o with Sketchpad reasons with interleaved visual and textual steps. For more, visit our project page: 📌 For math tasks, ✏️Sketchpad allows LLMs to draw auxiliary lines on geometry diagrams, plotting functions, graphs, and even games. GPT-4o does math better when it can sketch! (+12.7% acc on average) 📌 For computer vision tasks, ✏️Sketchpad allows LLMs to sketch with vision specialists (e.g., GroundingDINO draws bounding boxes, SegmentAnything draws masks). Sketchpad substantially improves GPT-4o's vision abilities. GPT-4o + Sketchpad compared with prior SOTAs: 1️⃣ V*Bench: 75.4% -> 80.3% 2️⃣ BLINK correspondence: 42.4% -> 80.8% 3️⃣ BLINK relative depth: 67.7% -> 83.9% 4️⃣ BLINK spatial relation: 76.2% -> 81.1% ... See more interesting examples in the thread!

Humans draw to facilitate reasoning and communication. Why not let LLMs do so? 🚀We introduce✏️Sketchpad, which gives multimodal LLMs a sketchpad to draw and facilitate reasoning! Sketchpad gives GPT-4o great boosts on many vision and math tasks 📈 The video shows how GPT-4o with Sketchpad reasons with interleaved visual and textual steps. For more, visit our project page: 📌 For math tasks, ✏️Sketchpad allows LLMs to draw auxiliary lines on geometry diagrams, plotting functions, graphs, and even games. GPT-4o does math better when it can sketch! (+12.7% acc on average) 📌 For computer vision tasks, ✏️Sketchpad allows LLMs to sketch with vision specialists (e.g., GroundingDINO draws bounding boxes, SegmentAnything draws masks). Sketchpad substantially improves GPT-4o's vision abilities. GPT-4o + Sketchpad compared with prior SOTAs: 1️⃣ V*Bench: 75.4% -> 80.3% 2️⃣ BLINK correspondence: 42.4% -> 80.8% 3️⃣ BLINK relative depth: 67.7% -> 83.9% 4️⃣ BLINK spatial relation: 76.2% -> 81.1% ... See more interesting examples in the thread!

Yushi Hu

145,048 次观看 • 2 年前

📢Happy to present Convex Splatting, a novel way for 3D reconstruction based on 3D smooth convexes. For the first time, a splatting-based method reaches the quality of NeRF sota methods but with real-time rendering and few primitives!! I expect this to replace Gaussian splatting for 3D in the coming months. CODE RELEASED TODAY! joint work with collaborators from Université de Liège Visual Geometry Group (VGG) , KAUST Computer Vision Lab (IVUL) a thread 🧵 1/n

📢Happy to present Convex Splatting, a novel way for 3D reconstruction based on 3D smooth convexes. For the first time, a splatting-based method reaches the quality of NeRF sota methods but with real-time rendering and few primitives!! I expect this to replace Gaussian splatting for 3D in the coming months. CODE RELEASED TODAY! joint work with collaborators from Université de Liège Visual Geometry Group (VGG) , KAUST Computer Vision Lab (IVUL) a thread 🧵 1/n

Abdullah Hamdi

71,661 次观看 • 1 年前

ViPE: Video Pose Engine for 3D Geometric Perception Contributions: • A robust and efficient framework, ViPE, for estimating camera parameters and dense depth from diverse, in-the-wild videos. • A system design that integrates the strengths of classical SLAM (efficiency, scalability) and learned models (robustness), with key improvements in efficiency, dynamic object handling, and depth quality over prior work. • A large-scale dataset of annotated videos, created using ViPE, to facilitate future research in 3D computer vision.

ViPE: Video Pose Engine for 3D Geometric Perception Contributions: • A robust and efficient framework, ViPE, for estimating camera parameters and dense depth from diverse, in-the-wild videos. • A system design that integrates the strengths of classical SLAM (efficiency, scalability) and learned models (robustness), with key improvements in efficiency, dynamic object handling, and depth quality over prior work. • A large-scale dataset of annotated videos, created using ViPE, to facilitate future research in 3D computer vision.

MrNeRF

42,553 次观看 • 11 个月前

How far can a very simple eye go in solving vision tasks? Like a 1-pixel camera? Humans have one of the greatest eyes in nature, while many animals have significantly simpler eyes and visual systems yet show complex perceptual behavior. In an interesting project, we find that many computer vision tasks can be solved without a typical camera and with such simple 1-pixel sensors (photoreceptors). We also find that proper design (e.g., where to place the photoreceptors strategically) makes a big difference, so we developed a computational design method to find them. 🌐 👁️[Solving Vision Tasks with Simple Photoreceptors Instead of Cameras] 🧵1/n

How far can a very simple eye go in solving vision tasks? Like a 1-pixel camera? Humans have one of the greatest eyes in nature, while many animals have significantly simpler eyes and visual systems yet show complex perceptual behavior. In an interesting project, we find that many computer vision tasks can be solved without a typical camera and with such simple 1-pixel sensors (photoreceptors). We also find that proper design (e.g., where to place the photoreceptors strategically) makes a big difference, so we developed a computational design method to find them. 🌐 👁️[Solving Vision Tasks with Simple Photoreceptors Instead of Cameras] 🧵1/n

Amir Zamir

75,892 次观看 • 2 年前

3D Object Tracking without Training Data? In our nature Machine Intelligence paper ( we recast 3D tracking as an inverse neural rendering task where we fit a scene graph to an image that best explains this image. The method generalizes to completely unseen datasets and is explainable. Project and Code: Fun collaboration between Princeton Computer Science and Torc Robotics, with Julian Ost and Tanushree Banerjee leading this project.

3D Object Tracking without Training Data? In our nature Machine Intelligence paper ( we recast 3D tracking as an inverse neural rendering task where we fit a scene graph to an image that best explains this image. The method generalizes to completely unseen datasets and is explainable. Project and Code: Fun collaboration between Princeton Computer Science and Torc Robotics, with Julian Ost and Tanushree Banerjee leading this project.

Felix Heide

27,858 次观看 • 11 个月前

Scaling 3D scene data is a long-standing challenge in scene understanding, spatial reasoning, and robotics. Since scanning, reconstruction, and labeling are so labor-intensive, data scarcity has remained a major bottleneck. 🛑 To solve this, we propose SceneVerse++: Lifting Unlabeled Internet-level Data for 3D Scene Understanding (CVPR 2026). By reconstructing internet videos and annotating 3D scenes automatically, we’ve created a massive real-world dataset for end-to-end understanding. 🌐📐 SceneVerse++ makes it easy to scale "in-the-wild" 3D scenes toward more capable spatial reasoning systems. This significantly promotes progress in 3D VQA, visual navigation, and broader tasks in Embodied AI and Robotics. 🤖🦾 We are fully open-sourced! Check out the paper, code, and data here: 🌐 Project: 📄 Paper: 📊 Dataset: Code:

Scaling 3D scene data is a long-standing challenge in scene understanding, spatial reasoning, and robotics. Since scanning, reconstruction, and labeling are so labor-intensive, data scarcity has remained a major bottleneck. 🛑 To solve this, we propose SceneVerse++: Lifting Unlabeled Internet-level Data for 3D Scene Understanding (CVPR 2026). By reconstructing internet videos and annotating 3D scenes automatically, we’ve created a massive real-world dataset for end-to-end understanding. 🌐📐 SceneVerse++ makes it easy to scale "in-the-wild" 3D scenes toward more capable spatial reasoning systems. This significantly promotes progress in 3D VQA, visual navigation, and broader tasks in Embodied AI and Robotics. 🤖🦾 We are fully open-sourced! Check out the paper, code, and data here: 🌐 Project: 📄 Paper: 📊 Dataset: Code:

Siyuan Huang

12,612 次观看 • 3 个月前

There's a certain kind of energy that only a room full of believers can create. The Avaada Electro Townhall had exactly that. Across functions, across roles, the team came together to align on the vision, celebrate the journey so far, and look ahead at everything we're building. The activities, the conversations, the spirit in that room were entirely on another level. This is what growth looks like from the inside. Avaada Electro

There's a certain kind of energy that only a room full of believers can create. The Avaada Electro Townhall had exactly that. Across functions, across roles, the team came together to align on the vision, celebrate the journey so far, and look ahead at everything we're building. The activities, the conversations, the spirit in that room were entirely on another level. This is what growth looks like from the inside. Avaada Electro

Vineet Mittal

1,075,600 次观看 • 2 个月前

📢 Lyra: Generative 3D Scene Reconstruction via Video Diffusion Model Self-Distillation Got only one or a few images and wondering if recovering the 3D environment is a reconstruction or generation problem? Why not do it with a generative reconstruction model! We show that a camera-conditioned video diffusion model can be transformed into a generative reconstruction model that directly outputs a high-quality 3D Gaussian Splatting representation through self-distillation, without requiring real-world training data. Check out our results in the video (wait for dynamic scenes in the second half!) : Project Page: Code and Models: Paper:

📢 Lyra: Generative 3D Scene Reconstruction via Video Diffusion Model Self-Distillation Got only one or a few images and wondering if recovering the 3D environment is a reconstruction or generation problem? Why not do it with a generative reconstruction model! We show that a camera-conditioned video diffusion model can be transformed into a generative reconstruction model that directly outputs a high-quality 3D Gaussian Splatting representation through self-distillation, without requiring real-world training data. Check out our results in the video (wait for dynamic scenes in the second half!) : Project Page: Code and Models: Paper:

Sherwin Bahmani

66,647 次观看 • 10 个月前

This AI paper just solved Google Earth's biggest problem. Satellites look down. Humans look across. That perspective gap is why 3D maps are limited to cities you can blanket with aerial flyovers. Skyfall-GS bridges the gap by synthesizing the views we never captured - rebuilding missing facades and street-level geometry using the world knowledge of diffusion models. And it does so with remarkable consistency. This is a taste of how we go from 3D maps in 3,000 cities to the entire planet. Watch my full video for the rundown:

This AI paper just solved Google Earth's biggest problem. Satellites look down. Humans look across. That perspective gap is why 3D maps are limited to cities you can blanket with aerial flyovers. Skyfall-GS bridges the gap by synthesizing the views we never captured - rebuilding missing facades and street-level geometry using the world knowledge of diffusion models. And it does so with remarkable consistency. This is a taste of how we go from 3D maps in 3,000 cities to the entire planet. Watch my full video for the rundown:

Bilawal Sidhu

135,003 次观看 • 8 个月前

THIS GUY VIBE CODED A TRUE 3D PROPERTY TOUR TOOL WITH CLAUDE CODE not the fake 360 photo stitching that matterport does, actual 3D right now if you're a real estate agent and want a property tour you need: > a matterport camera ($3000+) > a photographer who knows how to use it > matterport's monthly subscription > and you still get a glorified panorama, not real 3D this guy built a tool that takes your existing captures (camera files, drone shots, 360 photos, EVEN phone captures) and turns them into a real interactive 3D tour in one workflow no specialized hardware, no photographer, no switching between 5 different tools real estate agents, property managers, airbnb hosts, architects, interior designers all of them are paying hundreds per property for something this tool does from captures they already have the painful part was never understanding the end result. everyone knows what a 3D tour looks like. the pain is going from a pile of messy capture files to something usable without it turning into a technical project this solves that with one workflow you dump your files in and get a 3D tour out insane what you can do with vibe coding

THIS GUY VIBE CODED A TRUE 3D PROPERTY TOUR TOOL WITH CLAUDE CODE not the fake 360 photo stitching that matterport does, actual 3D right now if you're a real estate agent and want a property tour you need: > a matterport camera ($3000+) > a photographer who knows how to use it > matterport's monthly subscription > and you still get a glorified panorama, not real 3D this guy built a tool that takes your existing captures (camera files, drone shots, 360 photos, EVEN phone captures) and turns them into a real interactive 3D tour in one workflow no specialized hardware, no photographer, no switching between 5 different tools real estate agents, property managers, airbnb hosts, architects, interior designers all of them are paying hundreds per property for something this tool does from captures they already have the painful part was never understanding the end result. everyone knows what a 3D tour looks like. the pain is going from a pile of messy capture files to something usable without it turning into a technical project this solves that with one workflow you dump your files in and get a 3D tour out insane what you can do with vibe coding

Om Patel

157,274 次观看 • 2 个月前

Infinite Photorealistic Worlds using Procedural Generation paper page: introduce Infinigen, a procedural generator of photorealistic 3D scenes of the natural world. Infinigen is entirely procedural: every asset, from shape to texture, is generated from scratch via randomized mathematical rules, using no external source and allowing infinite variation and composition. Infinigen offers broad coverage of objects and scenes in the natural world including plants, animals, terrains, and natural phenomena such as fire, cloud, rain, and snow. Infinigen can be used to generate unlimited, diverse training data for a wide range of computer vision tasks including object detection, semantic segmentation, optical flow, and 3D reconstruction. We expect Infinigen to be a useful resource for computer vision research and beyond.

Infinite Photorealistic Worlds using Procedural Generation paper page: introduce Infinigen, a procedural generator of photorealistic 3D scenes of the natural world. Infinigen is entirely procedural: every asset, from shape to texture, is generated from scratch via randomized mathematical rules, using no external source and allowing infinite variation and composition. Infinigen offers broad coverage of objects and scenes in the natural world including plants, animals, terrains, and natural phenomena such as fire, cloud, rain, and snow. Infinigen can be used to generate unlimited, diverse training data for a wide range of computer vision tasks including object detection, semantic segmentation, optical flow, and 3D reconstruction. We expect Infinigen to be a useful resource for computer vision research and beyond.

AK

275,398 次观看 • 3 年前

Exciting news! Our MedSAM is featured in Computer Vision News! 🎉🎉🎉🙌 Check it out: We are not stopping at papers and aiming to take integration to the next level by incorporating MedSAM with 3D Slicer, a top-tier medical imaging viewer. 🏥 **Segment Anything in Medical Images!** Read the paper here: Get your hands on the code: Explore MedSAM@3Dslice: Huge shoutout to the lead contributor, Jun Ma (JunMa), and a big thank you to Reza Asakereh for his invaluable contributions to MedSAMSlicer! 👏 #MedSAM #MedicalImaging

Exciting news! Our MedSAM is featured in Computer Vision News! 🎉🎉🎉🙌 Check it out: We are not stopping at papers and aiming to take integration to the next level by incorporating MedSAM with 3D Slicer, a top-tier medical imaging viewer. 🏥 Segment Anything in Medical Images! Read the paper here: Get your hands on the code: Explore MedSAM@3Dslice: Huge shoutout to the lead contributor, Jun Ma (JunMa), and a big thank you to Reza Asakereh for his invaluable contributions to MedSAMSlicer! 👏 #MedSAM #MedicalImaging

Bo Wang

19,527 次观看 • 2 年前

Humans learn and improve from failures. Similarly, foundation models adapt based on human feedback. Can we leverage this failure understanding to enhance robotics systems that use foundation models? Introducing AHA—a vision-language model for detecting and reasoning over failures in robotic manipulation. Project page: 🧵Thread👇 Aha!

Humans learn and improve from failures. Similarly, foundation models adapt based on human feedback. Can we leverage this failure understanding to enhance robotics systems that use foundation models? Introducing AHA—a vision-language model for detecting and reasoning over failures in robotic manipulation. Project page: 🧵Thread👇 Aha!

Jiafei Duan

48,777 次观看 • 1 年前

How precise can a robot get… without ever seeing the object move? Turns out, just a geometric model is enough. A robot hit 73 precise 3D goals in a row, using only a geometric model. No demonstrations. No imitation learning. No fancy vision models. The secret? Sample where the robot could make contact. Let local contact-implicit control take over from there. That’s it. ✅ Real-time performance ✅ Natural contact making and breaking ✅ Works on tricky tasks like pushing and rotating This approach mixes global planning with local MPC. Fast. Accurate. Sample-efficient. Thanks for sharing, Michael Posa ! 📍Watch it in action: Paper:

How precise can a robot get… without ever seeing the object move? Turns out, just a geometric model is enough. A robot hit 73 precise 3D goals in a row, using only a geometric model. No demonstrations. No imitation learning. No fancy vision models. The secret? Sample where the robot could make contact. Let local contact-implicit control take over from there. That’s it. ✅ Real-time performance ✅ Natural contact making and breaking ✅ Works on tricky tasks like pushing and rotating This approach mixes global planning with local MPC. Fast. Accurate. Sample-efficient. Thanks for sharing, Michael Posa ! 📍Watch it in action: Paper:

Ilir Aliu

19,012 次观看 • 1 年前

🍺 LagerNVS (CVPR 2026) 🍺 LagerNVS is a generalizable, feed-forward, real-time Novel View Synthesis network which - performs rendering in real time, - generalizes to in-the-wild data, - works with and without known source cameras, - sets a new state-of-the-art among deterministic methods, - can be paired with a diffusion decoder for generative extrapolation. LagerNVS shows that 3D biases are useful for Novel View Synthesis but explicit 3D representations are not required to achieve them. We use 3D biases in (1) architecture design and (2) pre-training: (1) In NVS with explicit 3D representations (3DGS, NeRF) reconstruction is typically difficult and slow, but rendering is much faster and simpler. We mimic this process in the network design: we use a large (1B params) encoder and a small, lightweight decoder (ViT-B). This allows increasing the network capacity while still achieving real-time rendering. (2) The encoder, initialized from VGGT, was pre-trained with 3D reconstruction objectives, making the initial features 3D aware. Both substantially improve performance. Project page: Code: Paper: Models: Work done with Jianyuan Minghao Chen Christian Rupprecht and Andrea Vedaldi

🍺 LagerNVS (CVPR 2026) 🍺 LagerNVS is a generalizable, feed-forward, real-time Novel View Synthesis network which - performs rendering in real time, - generalizes to in-the-wild data, - works with and without known source cameras, - sets a new state-of-the-art among deterministic methods, - can be paired with a diffusion decoder for generative extrapolation. LagerNVS shows that 3D biases are useful for Novel View Synthesis but explicit 3D representations are not required to achieve them. We use 3D biases in (1) architecture design and (2) pre-training: (1) In NVS with explicit 3D representations (3DGS, NeRF) reconstruction is typically difficult and slow, but rendering is much faster and simpler. We mimic this process in the network design: we use a large (1B params) encoder and a small, lightweight decoder (ViT-B). This allows increasing the network capacity while still achieving real-time rendering. (2) The encoder, initialized from VGGT, was pre-trained with 3D reconstruction objectives, making the initial features 3D aware. Both substantially improve performance. Project page: Code: Paper: Models: Work done with Jianyuan Minghao Chen Christian Rupprecht and Andrea Vedaldi

Stan Szymanowicz

31,651 次观看 • 4 个月前

✨ Made a new mini feature on Photo AI: [ Grab from 3d model ] So the problem is we're at that stage in time (typical for AI) where image-to-3d models are not good enough but are fun to play with, but we know they'll be good enough in 1-2 years With [ Make 3d model ] you already can turn any Photo AI pic into a 3d model but it still looks hyper clunky and deformed, but it works! One cool idea I had to make that more useful and made now: Let people make a 3d model then change the view of the it with the 3d viewer, then press [ o ] and it grabs a frame of the 3d That image you can then [ Remix ] (img2img), and it becomes a real photo again and that in turn you can then turn into a video again with [ Make video ] So that essentially gives you a fully freeform camera position control to take photos with One thing I need to fix is the background/skybox, I kinda need to take the original photo and remove the person and just get the background for the 3d model viewer, in this case it should be white, but it's a start!

✨ Made a new mini feature on Photo AI: [ Grab from 3d model ] So the problem is we're at that stage in time (typical for AI) where image-to-3d models are not good enough but are fun to play with, but we know they'll be good enough in 1-2 years With [ Make 3d model ] you already can turn any Photo AI pic into a 3d model but it still looks hyper clunky and deformed, but it works! One cool idea I had to make that more useful and made now: Let people make a 3d model then change the view of the it with the 3d viewer, then press [ o ] and it grabs a frame of the 3d That image you can then [ Remix ] (img2img), and it becomes a real photo again and that in turn you can then turn into a video again with [ Make video ] So that essentially gives you a fully freeform camera position control to take photos with One thing I need to fix is the background/skybox, I kinda need to take the original photo and remove the person and just get the background for the 3d model viewer, in this case it should be white, but it's a start!

@levelsio

119,210 次观看 • 1 年前