正在加载视频...

视频加载失败

返回首页

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...

siyuanhuang95's profile picture

Siyuan Huang

5,037 subscribers

12,612 次观看 • 3 个月前 •via X (Twitter)

LIVE

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

Incredible to see the Aria Digital Twin (ADT) dataset leveraged here! 🚀 ADT is a game-changer for AI—it bridges the gap between real-world sensor data and 1:1 3D virtual reconstructions by providing a hyper-accurate "gold-standard" benchmark. Using this data, the RADIO-ViPE team proved that "uncalibrated" predictions can be nearly as accurate as those from expensive, high-end sensor rigs. This is a massive step forward for robots and AI systems understanding 3D spaces in real-time. 👓✨ Paper: Dataset: 💡Nathan Yan
0:30

Incredible to see the Aria Digital Twin (ADT) dataset leveraged here! 🚀 ADT is a game-changer for AI—it bridges the gap between real-world sensor data and 1:1 3D virtual reconstructions by providing a hyper-accurate "gold-standard" benchmark. Using this data, the RADIO-ViPE team proved that "uncalibrated" predictions can be nearly as accurate as those from expensive, high-end sensor rigs. This is a massive step forward for robots and AI systems understanding 3D spaces in real-time. 👓✨ Paper: Dataset: 💡Nathan Yan

Project Aria @Meta

26,864 次观看 • 3 个月前

We are excited to share EMDB, a novel dataset of 3D human poses for in-the-wild monocular videos, including global trajectories. Data and toolkit code is now available. More details in the thread below. Project Page:
0:36

We are excited to share EMDB, a novel dataset of 3D human poses for in-the-wild monocular videos, including global trajectories. Data and toolkit code is now available. More details in the thread below. Project Page:

AIT Lab

14,613 次观看 • 2 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.
0:31

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

Large-scale Gaussian splats have reached a new level of realism. This is a well-known temple in Bangkok, reconstructed as a high-fidelity 3D environment from 360 captures. At this level, the boundary between video and 3D starts to disappear. But what you’re looking at is not a video. It’s a dense spatial representation of a real place, where geometry, texture, and structure are preserved and made machine-readable. This kind of 3D data can power Visual AI, Robotics navigation, VPS localization, XR experiences, world models, and next-generation spatial computing systems. Built with Over the Reality.
2:46

Large-scale Gaussian splats have reached a new level of realism. This is a well-known temple in Bangkok, reconstructed as a high-fidelity 3D environment from 360 captures. At this level, the boundary between video and 3D starts to disappear. But what you’re looking at is not a video. It’s a dense spatial representation of a real place, where geometry, texture, and structure are preserved and made machine-readable. This kind of 3D data can power Visual AI, Robotics navigation, VPS localization, XR experiences, world models, and next-generation spatial computing systems. Built with Over the Reality.

Over the Reality 🌐

347,259 次观看 • 2 个月前

Large-scale 3D Scene Generation (all scenes are real-time rendered)!! Physically-grounded generative data without hallucinations is the missing link for robot learning and testing at scale. We introduce a method that directly generates large-scale 3D driving scenes with accurate geometry, allowing for causal view synthesis and generation with object permanence and explicit 3D geometry. This also allows for extreme trajectory extrapolation without failure! We also show that we can build fully data-driven simulators for end-to-end learning with this approach. Project: with the amazing team of Julian Ost, Amogh Joshi , Andrea Ramazzina, Maximilian Bömer, Mario Bijelic.
0:36

Large-scale 3D Scene Generation (all scenes are real-time rendered)!! Physically-grounded generative data without hallucinations is the missing link for robot learning and testing at scale. We introduce a method that directly generates large-scale 3D driving scenes with accurate geometry, allowing for causal view synthesis and generation with object permanence and explicit 3D geometry. This also allows for extreme trajectory extrapolation without failure! We also show that we can build fully data-driven simulators for end-to-end learning with this approach. Project: with the amazing team of Julian Ost, Amogh Joshi , Andrea Ramazzina, Maximilian Bömer, Mario Bijelic.

Felix Heide

27,779 次观看 • 11 个月前

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.
0:35

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

Spatial reasoning is a major challenge for the foundation models today, even in simple tasks like arranging objects in 3D space. #CVPR2025 Introducing LayoutVLM, a differentiable optimization framework that uses VLM to spatially reason about diverse scene layouts from unlabeled assets and open-ended language instructions 1/n
0:45

Spatial reasoning is a major challenge for the foundation models today, even in simple tasks like arranging objects in 3D space. #CVPR2025 Introducing LayoutVLM, a differentiable optimization framework that uses VLM to spatially reason about diverse scene layouts from unlabeled assets and open-ended language instructions 1/n

Fan-Yun Sun

92,584 次观看 • 1 年前

NVIDIA AI Open-Sources ViPE (Video Pose Engine): A Powerful and Versatile 3D Video Annotation Tool for Spatial AI ViPE integrates bundle adjustment with dense optical flow, sparse keypoint tracking, and metric depth priors to estimate camera intrinsics, poses, and dense depth maps at 3–5 FPS on a single GPU. It significantly improves over prior uncalibrated pose estimation methods, achieving 18% and 50% error reduction on TUM and KITTI benchmarks, respectively, and shows robustness to dynamic scenes and diverse camera models. Beyond the method, the NVIDIA team also released a large-scale dataset comprising ~100K real-world internet videos, 1M AI-generated videos, and 2K panoramic videos (≈96M frames) annotated with metric depth and poses. This dataset and engine aim to accelerate training for spatial AI tasks such as 3D reconstruction, video generation, and robotics.... full analysis: paper: codes: NVIDIA NVIDIA AI NVIDIAnewsroom NVIDIA Robotics NVIDIA AIDev NVIDIAdeveloper
1:13

NVIDIA AI Open-Sources ViPE (Video Pose Engine): A Powerful and Versatile 3D Video Annotation Tool for Spatial AI ViPE integrates bundle adjustment with dense optical flow, sparse keypoint tracking, and metric depth priors to estimate camera intrinsics, poses, and dense depth maps at 3–5 FPS on a single GPU. It significantly improves over prior uncalibrated pose estimation methods, achieving 18% and 50% error reduction on TUM and KITTI benchmarks, respectively, and shows robustness to dynamic scenes and diverse camera models. Beyond the method, the NVIDIA team also released a large-scale dataset comprising ~100K real-world internet videos, 1M AI-generated videos, and 2K panoramic videos (≈96M frames) annotated with metric depth and poses. This dataset and engine aim to accelerate training for spatial AI tasks such as 3D reconstruction, video generation, and robotics.... full analysis: paper: codes: NVIDIA NVIDIA AI NVIDIAnewsroom NVIDIA Robotics NVIDIA AIDev NVIDIAdeveloper

Marktechpost AI Dev News ⚡

217,453 次观看 • 10 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:
0:50

📢 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

We are thrilled to share that our first paper from my new lab, Spateo ( for spatiotemporal modeling of molecular holograms, is now online in Cell: Spateo is a comprehensive analytical framework for 3D whole-embryo spatiotemporal modeling. Its advanced features include: • 3D alignment and reconstruction at the whole-mouse-embryo scale (see the animation). • 3D spatial domain digitization and cell-cell communication analysis to understand spatial gene expression gradients and both inter- and intracellular communication. • 3D morphometric and volumetric analyses along with 3D morphogenesis vector field modeling to quantify dynamics such as surface area, volume, and cell density across organs, and to dissect the interplay between morphogenesis factors and cell migration. • A “Google Earth”-like browser, Spateo-viewer ( and for interactive and intuitive exploration of 3D spatial data. • Additional features, such as RNA signal-based single-cell segmentation. We are also honored that Nature “News and Views” has highlighted this work as well: This is really an amazing outcome after two years' heroic revision process that rewrite the entire paper using a new data ( for whole mouse embryos.
1:24

We are thrilled to share that our first paper from my new lab, Spateo ( for spatiotemporal modeling of molecular holograms, is now online in Cell: Spateo is a comprehensive analytical framework for 3D whole-embryo spatiotemporal modeling. Its advanced features include: • 3D alignment and reconstruction at the whole-mouse-embryo scale (see the animation). • 3D spatial domain digitization and cell-cell communication analysis to understand spatial gene expression gradients and both inter- and intracellular communication. • 3D morphometric and volumetric analyses along with 3D morphogenesis vector field modeling to quantify dynamics such as surface area, volume, and cell density across organs, and to dissect the interplay between morphogenesis factors and cell migration. • A “Google Earth”-like browser, Spateo-viewer ( and for interactive and intuitive exploration of 3D spatial data. • Additional features, such as RNA signal-based single-cell segmentation. We are also honored that Nature “News and Views” has highlighted this work as well: This is really an amazing outcome after two years' heroic revision process that rewrite the entire paper using a new data ( for whole mouse embryos.

evo-devo

58,400 次观看 • 1 年前

1/5 🚀 Thrilled to open-source OSCAR 🤖 — an action-conditioned world model for robotics, led by the visiting student in my group Zhuoyuan Wu! It generalizes across different robot embodiments with precise action controllability. All trained on a single GH200 GPU, and outperforms existing open-sourced baselines, which have larger model capacity and need more compute. Everything is public, including training data. 📄 Paper: 🌐 Project: 💻 Code: 🤗 Robot data: 🤗 Human data: 🤗 Weights: #Robotics #WorldModels #AI #OpenSource
0:31

1/5 🚀 Thrilled to open-source OSCAR 🤖 — an action-conditioned world model for robotics, led by the visiting student in my group Zhuoyuan Wu! It generalizes across different robot embodiments with precise action controllability. All trained on a single GH200 GPU, and outperforms existing open-sourced baselines, which have larger model capacity and need more compute. Everything is public, including training data. 📄 Paper: 🌐 Project: 💻 Code: 🤗 Robot data: 🤗 Human data: 🤗 Weights: #Robotics #WorldModels #AI #OpenSource

Jun Gao

104,471 次观看 • 1 个月前

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.
0:29

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

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 次观看 • 3 年前

a robot can recognize every object in a room and still not know how to open a single drawer knowing there's a cabinet is scene understanding. knowing which handle to grab, which direction to pull, and that it's a drawer not a door is affordance understanding almost no dataset has it in 3D SceneFun3D: 14,800+ functional elements across 710 laser-scanned indoor scenes. every handle, knob, button, and switch labeled with its affordance, motion axis, motion type, and a natural language task description each scene's 3D point cloud with its iPad video recordings in fiftyone. the affordance annotations live in 3D and project into the video frames check it out here
0:30

a robot can recognize every object in a room and still not know how to open a single drawer knowing there's a cabinet is scene understanding. knowing which handle to grab, which direction to pull, and that it's a drawer not a door is affordance understanding almost no dataset has it in 3D SceneFun3D: 14,800+ functional elements across 710 laser-scanned indoor scenes. every handle, knob, button, and switch labeled with its affordance, motion axis, motion type, and a natural language task description each scene's 3D point cloud with its iPad video recordings in fiftyone. the affordance annotations live in 3D and project into the video frames check it out here

harpreet

18,800 次观看 • 1 个月前

Introducing FoundationMotion. A large-scale, video-derived motion annotation dataset & auto-labeling pipeline + advanced models for motion understanding. Fully open-source: code, datasets, and models, free to use and build on. Understanding motion is core to physical reasoning, yet today’s leading models still struggle with simple spatial actions like “turn right” or “move up” or “flip the toast” - mainly due to the lack of large, fine-grained motion datasets. We present FoundationMotion, a fully automated pipeline that: • detects & tracks objects in videos • extracts trajectories • uses LLMs + frames to generate rich motion captions & QA pairs → creating large-scale, high-quality motion datasets at scale. After fine-tuning the open-source models Qwen and NVILA on our annotations, these models now outperform the closed-source Gemini-3-Flash and GPT-5.1 on spatial understanding tasks across autonomous driving, robotics, and everyday scenarios. 📜Paper: 🌐Webpage: 💻 Code: 🕸️Model: 📊 Dataset: 👉 Interactive Demo: Let’s move research forward together. FoundationMotion is also referred to as Wolf V2 🐺, the second chapter in the Wolf series:
1:25

Introducing FoundationMotion. A large-scale, video-derived motion annotation dataset & auto-labeling pipeline + advanced models for motion understanding. Fully open-source: code, datasets, and models, free to use and build on. Understanding motion is core to physical reasoning, yet today’s leading models still struggle with simple spatial actions like “turn right” or “move up” or “flip the toast” - mainly due to the lack of large, fine-grained motion datasets. We present FoundationMotion, a fully automated pipeline that: • detects & tracks objects in videos • extracts trajectories • uses LLMs + frames to generate rich motion captions & QA pairs → creating large-scale, high-quality motion datasets at scale. After fine-tuning the open-source models Qwen and NVILA on our annotations, these models now outperform the closed-source Gemini-3-Flash and GPT-5.1 on spatial understanding tasks across autonomous driving, robotics, and everyday scenarios. 📜Paper: 🌐Webpage: 💻 Code: 🕸️Model: 📊 Dataset: 👉 Interactive Demo: Let’s move research forward together. FoundationMotion is also referred to as Wolf V2 🐺, the second chapter in the Wolf series:

Boyi Li

66,999 次观看 • 7 个月前

The first global, city-scale 3D map is taking shape, and it’s machine-readable. City-scale environments can now be reconstructed in high-fidelity, reaching a level of detail that is becoming almost indistinguishable from reality. This leap is made possible by large-scale mapping using just an Insta360 X5 and Over the Reality technology. So far, our dataset includes: - 220,000+ 3D mapped locations - 97M images - 1,000TB of spatial data Growing by more than 10,000+ newly mapped locations every week. Enabling Visual AI, Robotics, VPS, XR, and Digital twins.
0:27

The first global, city-scale 3D map is taking shape, and it’s machine-readable. City-scale environments can now be reconstructed in high-fidelity, reaching a level of detail that is becoming almost indistinguishable from reality. This leap is made possible by large-scale mapping using just an Insta360 X5 and Over the Reality technology. So far, our dataset includes: - 220,000+ 3D mapped locations - 97M images - 1,000TB of spatial data Growing by more than 10,000+ newly mapped locations every week. Enabling Visual AI, Robotics, VPS, XR, and Digital twins.

Over the Reality 🌐

69,605 次观看 • 3 个月前

📢 OneCanvas: 3D Scene Understanding via Panoramic Reprojection We extract features from video frames and reproject them into one occlusion-free view of the whole scene that a 2D VLM reads just like a normal image. We can center this view on any viewpoint, including an agent's own pose for situated reasoning. The same projection lets us create spatial training tasks with no human annotation, solvable only by reasoning over the 3D positions of real object features placed on an otherwise empty canvas. The result is a stock 2D VLM that reasons in 3D, setting a new state of the art across spatial benchmarks at far less compute. 🌐 ▶️ Great work by Bartłomiej Baranowski & Dave Zhenyu Chen
0:44

📢 OneCanvas: 3D Scene Understanding via Panoramic Reprojection We extract features from video frames and reproject them into one occlusion-free view of the whole scene that a 2D VLM reads just like a normal image. We can center this view on any viewpoint, including an agent's own pose for situated reasoning. The same projection lets us create spatial training tasks with no human annotation, solvable only by reasoning over the 3D positions of real object features placed on an otherwise empty canvas. The result is a stock 2D VLM that reasons in 3D, setting a new state of the art across spatial benchmarks at far less compute. 🌐 ▶️ Great work by Bartłomiej Baranowski & Dave Zhenyu Chen

Matthias Niessner

25,169 次观看 • 1 个月前

Alibaba presents MIMO Controllable Character Video Synthesis with Spatial Decomposed Modeling Character video synthesis aims to produce realistic videos of animatable characters within lifelike scenes. As a fundamental problem in the computer vision and graphics community, 3D works typically require multi-view captures for per-case training, which severely limits their applicability of modeling arbitrary characters in a short time. Recent 2D methods break this limitation via pre-trained diffusion models, but they struggle for pose generality and scene interaction. To this end, we propose MIMO, a novel framework which can not only synthesize character videos with controllable attributes (i.e., character, motion and scene) provided by simple user inputs, but also simultaneously achieve advanced scalability to arbitrary characters, generality to novel 3D motions, and applicability to interactive real-world scenes in a unified framework. The core idea is to encode the 2D video to compact spatial codes, considering the inherent 3D nature of video occurrence. Concretely, we lift the 2D frame pixels into 3D using monocular depth estimators, and decompose the video clip to three spatial components (i.e., main human, underlying scene, and floating occlusion) in hierarchical layers based on the 3D depth. These components are further encoded to canonical identity code, structured motion code and full scene code, which are utilized as control signals of synthesis process. The design of spatial decomposed modeling enables flexible user control, complex motion expression, as well as 3D-aware synthesis for scene interactions. Experimental results demonstrate effectiveness and robustness of the proposed method.
1:29

Alibaba presents MIMO Controllable Character Video Synthesis with Spatial Decomposed Modeling Character video synthesis aims to produce realistic videos of animatable characters within lifelike scenes. As a fundamental problem in the computer vision and graphics community, 3D works typically require multi-view captures for per-case training, which severely limits their applicability of modeling arbitrary characters in a short time. Recent 2D methods break this limitation via pre-trained diffusion models, but they struggle for pose generality and scene interaction. To this end, we propose MIMO, a novel framework which can not only synthesize character videos with controllable attributes (i.e., character, motion and scene) provided by simple user inputs, but also simultaneously achieve advanced scalability to arbitrary characters, generality to novel 3D motions, and applicability to interactive real-world scenes in a unified framework. The core idea is to encode the 2D video to compact spatial codes, considering the inherent 3D nature of video occurrence. Concretely, we lift the 2D frame pixels into 3D using monocular depth estimators, and decompose the video clip to three spatial components (i.e., main human, underlying scene, and floating occlusion) in hierarchical layers based on the 3D depth. These components are further encoded to canonical identity code, structured motion code and full scene code, which are utilized as control signals of synthesis process. The design of spatial decomposed modeling enables flexible user control, complex motion expression, as well as 3D-aware synthesis for scene interactions. Experimental results demonstrate effectiveness and robustness of the proposed method.

AK

148,998 次观看 • 1 年前

When we run out of good training data in reality, simulation is the next gold mine. Enters Infinigen: an open-source, procedurally generated, photorealistic dataset for 3D vision. The quality is stunning! No two worlds are the same. ▸ Every little detail is randomized and customizable, even the wrinkles on a flower petal! ▸ Diverse objects & scenes in the natural world: plants, animals, terrains; fire, cloud, rain, and snow. ▸ Groundtruth automatic annotations: optical flow, 3D scene flow, depth, surface normals, panoptic segmentation, occlusion boundaries. ▸ Written in Blender. Made by Jia Deng's lab at Princeton: ▸ Website: ▸ Code: ▸ Paper:
3:03

When we run out of good training data in reality, simulation is the next gold mine. Enters Infinigen: an open-source, procedurally generated, photorealistic dataset for 3D vision. The quality is stunning! No two worlds are the same. ▸ Every little detail is randomized and customizable, even the wrinkles on a flower petal! ▸ Diverse objects & scenes in the natural world: plants, animals, terrains; fire, cloud, rain, and snow. ▸ Groundtruth automatic annotations: optical flow, 3D scene flow, depth, surface normals, panoptic segmentation, occlusion boundaries. ▸ Written in Blender. Made by Jia Deng's lab at Princeton: ▸ Website: ▸ Code: ▸ Paper:

Jim Fan

363,656 次观看 • 3 年前

PointOdyssey: A Large-Scale Synthetic Dataset for Long-Term Point Tracking paper page: introduce PointOdyssey, a large-scale synthetic dataset, and data generation framework, for the training and evaluation of long-term fine-grained tracking algorithms. Our goal is to advance the state-of-the-art by placing emphasis on long videos with naturalistic motion. Toward the goal of naturalism, we animate deformable characters using real-world motion capture data, we build 3D scenes to match the motion capture environments, and we render camera viewpoints using trajectories mined via structure-from-motion on real videos. We create combinatorial diversity by randomizing character appearance, motion profiles, materials, lighting, 3D assets, and atmospheric effects. Our dataset currently includes 104 videos, averaging 2,000 frames long, with orders of magnitude more correspondence annotations than prior work. We show that existing methods can be trained from scratch in our dataset and outperform the published variants. Finally, we introduce modifications to the PIPs point tracking method, greatly widening its temporal receptive field, which improves its performance on PointOdyssey as well as on two real-world benchmarks.
0:33

PointOdyssey: A Large-Scale Synthetic Dataset for Long-Term Point Tracking paper page: introduce PointOdyssey, a large-scale synthetic dataset, and data generation framework, for the training and evaluation of long-term fine-grained tracking algorithms. Our goal is to advance the state-of-the-art by placing emphasis on long videos with naturalistic motion. Toward the goal of naturalism, we animate deformable characters using real-world motion capture data, we build 3D scenes to match the motion capture environments, and we render camera viewpoints using trajectories mined via structure-from-motion on real videos. We create combinatorial diversity by randomizing character appearance, motion profiles, materials, lighting, 3D assets, and atmospheric effects. Our dataset currently includes 104 videos, averaging 2,000 frames long, with orders of magnitude more correspondence annotations than prior work. We show that existing methods can be trained from scratch in our dataset and outperform the published variants. Finally, we introduce modifications to the PIPs point tracking method, greatly widening its temporal receptive field, which improves its performance on PointOdyssey as well as on two real-world benchmarks.

AK

122,560 次观看 • 3 年前