Video wird geladen...

Video konnte nicht geladen werden

Beim Laden dieses Videos ist ein Problem aufgetreten. Dies könnte an einem vorübergehenden Netzwerkproblem liegen oder das Video ist möglicherweise nicht verfügbar.

Motion cues from human videos + Reasoning from VLMs enables 3D hand trajectory prediction in-the-wild for novel tasks in novel scenes! Very excited to share the EgoMan project, a huge effort led by Mingfei Chen during an internship with us at Meta. Video summary ⬇️

Homanga Bharadhwaj

3,209 subscribers

10,539 Aufrufe • vor 8 Monaten •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

0 Kommentare

Keine Kommentare verfügbar

Kommentare vom Original-Post werden hier angezeigt

Ähnliche Videos

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:

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

14,625 Aufrufe • vor 3 Jahren

The most frustrating part of imitation learning is collecting huge amounts of teleop data. But why teleop robots when robots can learn by watching us? Introducing Point Policy, a novel framework that enables robots to learn from human videos without any teleop, sim2real, or RL.

The most frustrating part of imitation learning is collecting huge amounts of teleop data. But why teleop robots when robots can learn by watching us? Introducing Point Policy, a novel framework that enables robots to learn from human videos without any teleop, sim2real, or RL.

Siddhant Haldar

69,056 Aufrufe • vor 1 Jahr

We relived Michelangelo in neural network style!! Super excited to finally share Neuralangelo 🛠 -- 3D surface reconstruction from RGB videos with extremely high fidelity! 🤩 To appear at #CVPR2023 project page: paper: 🧵⬇️ (1/4)

We relived Michelangelo in neural network style!! Super excited to finally share Neuralangelo 🛠 -- 3D surface reconstruction from RGB videos with extremely high fidelity! 🤩 To appear at #CVPR2023 project page: paper: 🧵⬇️ (1/4)

Chen-Hsuan Lin

253,380 Aufrufe • vor 3 Jahren

Robot Learning needs 4D world models! Robot Learning needs 4D world models! Robot Learning needs 4D world models! We introduce TesserAct, a 4D embodied world model that can simulate how agents interact with the 3D world over time! We achieve this by simply extending a pre-trained 2D video generation model to jointly predict RGB, depth, and surface normals. It enables: 1️⃣ Much better policy learning in the wild 2️⃣ Temporal + spatial coherence in 4D dynamic prediction 3️⃣ Novel view synthesis for embodied scenes Code: Paper Link: Project page:

Robot Learning needs 4D world models! Robot Learning needs 4D world models! Robot Learning needs 4D world models! We introduce TesserAct, a 4D embodied world model that can simulate how agents interact with the 3D world over time! We achieve this by simply extending a pre-trained 2D video generation model to jointly predict RGB, depth, and surface normals. It enables: 1️⃣ Much better policy learning in the wild 2️⃣ Temporal + spatial coherence in 4D dynamic prediction 3️⃣ Novel view synthesis for embodied scenes Code: Paper Link: Project page:

Chuang Gan

43,265 Aufrufe • vor 1 Jahr

📢 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

📢 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

25,386 Aufrufe • vor 2 Monaten

Fast View Synthesis of Casual Videos paper page: Novel view synthesis from an in-the-wild video is difficult due to challenges like scene dynamics and lack of parallax. While existing methods have shown promising results with implicit neural radiance fields, they are slow to train and render. This paper revisits explicit video representations to synthesize high-quality novel views from a monocular video efficiently. We treat static and dynamic video content separately. Specifically, we build a global static scene model using an extended plane-based scene representation to synthesize temporally coherent novel video. Our plane-based scene representation is augmented with spherical harmonics and displacement maps to capture view-dependent effects and model non-planar complex surface geometry. We opt to represent the dynamic content as per-frame point clouds for efficiency. While such representations are inconsistency-prone, minor temporal inconsistencies are perceptually masked due to motion. We develop a method to quickly estimate such a hybrid video representation and render novel views in real time. Our experiments show that our method can render high-quality novel views from an in-the-wild video with comparable quality to state-of-the-art methods while being 100x faster in training and enabling real-time rendering.

Fast View Synthesis of Casual Videos paper page: Novel view synthesis from an in-the-wild video is difficult due to challenges like scene dynamics and lack of parallax. While existing methods have shown promising results with implicit neural radiance fields, they are slow to train and render. This paper revisits explicit video representations to synthesize high-quality novel views from a monocular video efficiently. We treat static and dynamic video content separately. Specifically, we build a global static scene model using an extended plane-based scene representation to synthesize temporally coherent novel video. Our plane-based scene representation is augmented with spherical harmonics and displacement maps to capture view-dependent effects and model non-planar complex surface geometry. We opt to represent the dynamic content as per-frame point clouds for efficiency. While such representations are inconsistency-prone, minor temporal inconsistencies are perceptually masked due to motion. We develop a method to quickly estimate such a hybrid video representation and render novel views in real time. Our experiments show that our method can render high-quality novel views from an in-the-wild video with comparable quality to state-of-the-art methods while being 100x faster in training and enabling real-time rendering.

AK

20,668 Aufrufe • vor 2 Jahren

Very Powerful but very simple Prompting technique. Simply ask the LLM to re-read the question - and this significantly boosts LLM reasoning across diverse tasks and model types. 💡 Repeats question input twice in prompt, unlocks latent reasoning potential **Original Problem** 🤔: Decoder-only LLMs with unidirectional attention struggle with nuanced reasoning tasks due to limited global understanding of input questions. **Key Insights from this Paper **💡: • Re-reading (RE2) input enhances reasoning by improving question comprehension • Enables "bidirectional" understanding in unidirectional LLMs • Compatible with existing thought-eliciting prompting methods • Effective across various LLM types and reasoning tasks

Very Powerful but very simple Prompting technique. Simply ask the LLM to re-read the question - and this significantly boosts LLM reasoning across diverse tasks and model types. 💡 Repeats question input twice in prompt, unlocks latent reasoning potential Original Problem 🤔: Decoder-only LLMs with unidirectional attention struggle with nuanced reasoning tasks due to limited global understanding of input questions. Key Insights from this Paper 💡: • Re-reading (RE2) input enhances reasoning by improving question comprehension • Enables "bidirectional" understanding in unidirectional LLMs • Compatible with existing thought-eliciting prompting methods • Effective across various LLM types and reasoning tasks

Rohan Paul

169,522 Aufrufe • vor 2 Jahren

Excited to share our #NeurIPS2025 work on learning motion hierarchies! We introduce a general hierarchical graph learning method that learns structured, interpretable motion directly from data, no prior structure or assumptions needed!!! Project and Paper: Amazing work led by William Koch, Cheng Zheng, and Baiang Li ! See us in San Diego for #NeurIPS2025!

Excited to share our #NeurIPS2025 work on learning motion hierarchies! We introduce a general hierarchical graph learning method that learns structured, interpretable motion directly from data, no prior structure or assumptions needed!!! Project and Paper: Amazing work led by William Koch, Cheng Zheng, and Baiang Li ! See us in San Diego for #NeurIPS2025!

Felix Heide

25,342 Aufrufe • vor 9 Monaten

Happy Final Space Friday! One of many teasers I'm editing. Daz Tibbles added little motion to the a few pages. This is all I have to post while we're waiting for printing to complete. Samples should be coming in a few weeks. In the meantime I'm going to keep editing a bunch of these with dialogue from the novel while mixing shots from the show with the pages from the novel. When we get closer to the release you'll see a BIG push with these teasers. More soon! -Olan PRE-ORDER:

Happy Final Space Friday! One of many teasers I'm editing. Daz Tibbles added little motion to the a few pages. This is all I have to post while we're waiting for printing to complete. Samples should be coming in a few weeks. In the meantime I'm going to keep editing a bunch of these with dialogue from the novel while mixing shots from the show with the pages from the novel. When we get closer to the release you'll see a BIG push with these teasers. More soon! -Olan PRE-ORDER:

Final Space

30,540 Aufrufe • vor 9 Monaten

Excited to announce that Sola has raised a $17.5M Series A led by a16z with support from Conviction Y Combinator, bringing total funding to $21M 🚀 From the start, we set out to reimagine human-AI interaction to push the boundaries of process automation. Our agents watch how people do tasks on-screen, then handle those tasks automatically, even in legacy tools.

Excited to announce that Sola has raised a $17.5M Series A led by a16z with support from Conviction Y Combinator, bringing total funding to $21M 🚀 From the start, we set out to reimagine human-AI interaction to push the boundaries of process automation. Our agents watch how people do tasks on-screen, then handle those tasks automatically, even in legacy tools.

Neil Deshmukh

334,694 Aufrufe • vor 1 Jahr

📢📢📢 Excited to share our ICLR25 work, ArtGS, which can reconstruct articulated objects and scenes from human-scene interactions. 💻🖱️🧱🪑📖 Understanding physics and articulation is extremely important. With ArtGS, we can build a digital and simulatable replica of the real 3D world with minimal human effort!

📢📢📢 Excited to share our ICLR25 work, ArtGS, which can reconstruct articulated objects and scenes from human-scene interactions. 💻🖱️🧱🪑📖 Understanding physics and articulation is extremely important. With ArtGS, we can build a digital and simulatable replica of the real 3D world with minimal human effort!

Siyuan Huang

12,819 Aufrufe • vor 1 Jahr

Check out this amazing behind the scenes video of true, novel discovery at work. Tim Bennett in situ at 142 meters collecting a new species of Chromis in Flora Reef, filmed by Ghislain Bardout of UNDER THE POLE during our recent mesophotic expedition to the Coral Sea.

Check out this amazing behind the scenes video of true, novel discovery at work. Tim Bennett in situ at 142 meters collecting a new species of Chromis in Flora Reef, filmed by Ghislain Bardout of UNDER THE POLE during our recent mesophotic expedition to the Coral Sea.

KaiTheFishGuy

18,272 Aufrufe • vor 2 Jahren

Spatio-Temporal Reconstruction Model for Large-Scale Outdoor Scenes Contributions: • We propose STORM, the first feed-forward, self-supervised method for fast and accurate reconstruction of dynamic 3D scenes from sparse, multi-timestep, posed camera images. • Our bottom-up framework aggregates and transforms per-frame 3D Gaussian Splats into a cohesive scene representation, enabling self-supervised motion estimation. Furthermore, we introduce motion tokens that capture common motion primitives and regularize motion predictions, facilitating dynamic motion group segmentation without explicit motion or correspondence supervision. • We present several enhancements for in-the-wild scenarios, including sky modeling, camera exposure inconsistency handling, large novel-view extrapolation, and fine-grained human motions reconstruction, making STORM well-suited for real-world applications.

Spatio-Temporal Reconstruction Model for Large-Scale Outdoor Scenes Contributions: • We propose STORM, the first feed-forward, self-supervised method for fast and accurate reconstruction of dynamic 3D scenes from sparse, multi-timestep, posed camera images. • Our bottom-up framework aggregates and transforms per-frame 3D Gaussian Splats into a cohesive scene representation, enabling self-supervised motion estimation. Furthermore, we introduce motion tokens that capture common motion primitives and regularize motion predictions, facilitating dynamic motion group segmentation without explicit motion or correspondence supervision. • We present several enhancements for in-the-wild scenarios, including sky modeling, camera exposure inconsistency handling, large novel-view extrapolation, and fine-grained human motions reconstruction, making STORM well-suited for real-world applications.

MrNeRF

53,292 Aufrufe • vor 1 Jahr

Wrapping up the year and coinciding with #NeurIPS2024, today at Meta FAIR we’re releasing a collection of nine new open source AI research artifacts across our work in developing agents, robustness & safety and new architectures. More in the video from Joelle Pineau. All of this work is part of FAIR’s continued work towards the goal of achieving advanced machine intelligence A few highlights from what we’re releasing today: • Meta Motivo: A first-of-its-kind behavioral foundation model that controls the movements of a virtual embodied humanoid agent to perform complex tasks. • Meta Video Seal: a state-of-the art comprehensive framework for neural video watermarking. • Meta Explore Theory-of-Mind: A program-guided adversarial data generation for theory of mind reasoning. • Meta Large Concept Models: A fundamentally different training paradigm for language modeling that decouples reasoning from language representation. And much more! We’re excited to share this work with the research community and look forward to seeing how it inspires new innovation across the field. Details and access to everything released by FAIR today ➡️

Wrapping up the year and coinciding with #NeurIPS2024, today at Meta FAIR we’re releasing a collection of nine new open source AI research artifacts across our work in developing agents, robustness & safety and new architectures. More in the video from Joelle Pineau. All of this work is part of FAIR’s continued work towards the goal of achieving advanced machine intelligence A few highlights from what we’re releasing today: • Meta Motivo: A first-of-its-kind behavioral foundation model that controls the movements of a virtual embodied humanoid agent to perform complex tasks. • Meta Video Seal: a state-of-the art comprehensive framework for neural video watermarking. • Meta Explore Theory-of-Mind: A program-guided adversarial data generation for theory of mind reasoning. • Meta Large Concept Models: A fundamentally different training paradigm for language modeling that decouples reasoning from language representation. And much more! We’re excited to share this work with the research community and look forward to seeing how it inspires new innovation across the field. Details and access to everything released by FAIR today ➡️

AI at Meta

156,123 Aufrufe • vor 1 Jahr

This robodog aims to remove humans from hazardous work environments The Robot Teleoperativo 2 project out of the Dynamic Legged Systems lab has developed an advanced teleoperation system designed to operate in high-risk environments, minimizing dangers to human workers. By integrating cutting-edge technologies in tele-locomotion, tele-manipulation, and remote human-robot interaction, the system enables precise, dual-arm control for complex tasks in hazardous conditions.

This robodog aims to remove humans from hazardous work environments The Robot Teleoperativo 2 project out of the Dynamic Legged Systems lab has developed an advanced teleoperation system designed to operate in high-risk environments, minimizing dangers to human workers. By integrating cutting-edge technologies in tele-locomotion, tele-manipulation, and remote human-robot interaction, the system enables precise, dual-arm control for complex tasks in hazardous conditions.

Circuit

22,831 Aufrufe • vor 1 Jahr

📢📢📢 Excited to share our new work *Autonomous Character-Scene Interaction Synthesis from Text Instruction* (Siggraph Asia 24). It presents a unified model for flexible scene-conditioned motion generation given text, scene, trajectory conditions. The results with smooth interaction look very impressive! 📰Paper: Project: Code and data will be released soon.

📢📢📢 Excited to share our new work Autonomous Character-Scene Interaction Synthesis from Text Instruction (Siggraph Asia 24). It presents a unified model for flexible scene-conditioned motion generation given text, scene, trajectory conditions. The results with smooth interaction look very impressive! 📰Paper: Project: Code and data will be released soon.

Siyuan Huang

11,451 Aufrufe • vor 1 Jahr

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.

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

149,079 Aufrufe • vor 2 Jahren

MotionGPT: Human Motion as a Foreign Language paper page: Though the advancement of pre-trained large language models unfolds, the exploration of building a unified model for language and other multi-modal data, such as motion, remains challenging and untouched so far. Fortunately, human motion displays a semantic coupling akin to human language, often perceived as a form of body language. By fusing language data with large-scale motion models, motion-language pre-training that can enhance the performance of motion-related tasks becomes feasible. Driven by this insight, we propose MotionGPT, a unified, versatile, and user-friendly motion-language model to handle multiple motion-relevant tasks. Specifically, we employ the discrete vector quantization for human motion and transfer 3D motion into motion tokens, similar to the generation process of word tokens. Building upon this "motion vocabulary", we perform language modeling on both motion and text in a unified manner, treating human motion as a specific language. Moreover, inspired by prompt learning, we pre-train MotionGPT with a mixture of motion-language data and fine-tune it on prompt-based question-and-answer tasks. Extensive experiments demonstrate that MotionGPT achieves state-of-the-art performances on multiple motion tasks including text-driven motion generation, motion captioning, motion prediction, and motion in-between.

MotionGPT: Human Motion as a Foreign Language paper page: Though the advancement of pre-trained large language models unfolds, the exploration of building a unified model for language and other multi-modal data, such as motion, remains challenging and untouched so far. Fortunately, human motion displays a semantic coupling akin to human language, often perceived as a form of body language. By fusing language data with large-scale motion models, motion-language pre-training that can enhance the performance of motion-related tasks becomes feasible. Driven by this insight, we propose MotionGPT, a unified, versatile, and user-friendly motion-language model to handle multiple motion-relevant tasks. Specifically, we employ the discrete vector quantization for human motion and transfer 3D motion into motion tokens, similar to the generation process of word tokens. Building upon this "motion vocabulary", we perform language modeling on both motion and text in a unified manner, treating human motion as a specific language. Moreover, inspired by prompt learning, we pre-train MotionGPT with a mixture of motion-language data and fine-tune it on prompt-based question-and-answer tasks. Extensive experiments demonstrate that MotionGPT achieves state-of-the-art performances on multiple motion tasks including text-driven motion generation, motion captioning, motion prediction, and motion in-between.

AK

125,353 Aufrufe • vor 3 Jahren