Video yükleniyor...

Video Yüklenemedi

Bu video yüklenirken bir sorun oluştu. Bu geçici bir ağ sorunundan kaynaklanıyor olabilir veya video kullanılamıyor olabilir.

Ana Sayfaya Dön

Existing 3D human manipulation datasets are valuable, but are limited in scale and diversity. At #CVPR2025, we will introduce GigaHands👐 which, to our knowledge, is the most extensive 3D bimanual manipulation, interaction, and gesture dataset.🧵👇(1/9)

Srinath Sridhar

5,112 subscribers

13,443 görüntüleme • 1 yıl önce •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

11 Yorum

Srinath Sridhar profil fotoğrafı

Srinath Sridhar1 yıl önce

Some statistics about GigaHands 📊 🕒 34 hrs of manual activities 👥 56 participants 🧱 417 objects 🎞️ 14k 3D motion sequences 🖼️ 183M frames 📝 84k text annotations We hope the dataset opens new research directions in AI, robotics, computer vision, and animation! 🤖🎬🖥️ (2/9)

Srinath Sridhar profil fotoğrafı

Srinath Sridhar1 yıl önce

🛠️ How did we build GigaHands? ✅ Markerless multi-camera motion capture with 51 cameras ✅ Procedurally-generated instructions ensuring comprehensive coverage of bimanual interactions ✅ Rich data captured without intrusive markers! (3/9)

Srinath Sridhar profil fotoğrafı

Srinath Sridhar1 yıl önce

📑 It has rich annotations for: ✋ 3D hand shape & pose 📦 3D rigid object shape & pose; object scans 🧩 Hand-object segmentation masks 📍 2D/3D keypoints 🎥 Camera poses 📝 Detailed textual descriptions All captured using a markerless, multi-camera setup! 📸(4/9)

Srinath Sridhar profil fotoğrafı

Srinath Sridhar1 yıl önce

GigaHands enables applications like text-conditioned motion generation, i.e., describe actions in text 👉 Generate realistic hand interactions! 🤝✨ (5/9)

Srinath Sridhar profil fotoğrafı

Srinath Sridhar1 yıl önce

Or motion captioning to generate textual descriptions from hand motions—even across diverse datasets! 📖🔄 (6/9)

Srinath Sridhar profil fotoğrafı

Srinath Sridhar1 yıl önce

Since GigaHands has dense cameras, we can reconstruct dynamic 3D hand-object interactions in great detail 🛠️🔍 (7/9)

Srinath Sridhar profil fotoğrafı

Srinath Sridhar1 yıl önce

Tracking data from GigaHands can also enable motion retargeting to robotic and virtual hands. 🤖🖐️ (8/9)

Srinath Sridhar profil fotoğrafı

Srinath Sridhar1 yıl önce

This work was led by my PhD student, @RaoFu79761158 in collaboration with Dingxi Zhang, Alex Jiang, Wanjia Fu, Austin Funk, and Daniel Ritchie @BrownVisualComp. Paper, data and code released: 🌐 #GigaHands #CVPR2025 #AI #ComputerVision #Robotics (9/9)

VistaShares profil fotoğrafı

VistaShares1 yıl önce

From semiconductors to data centers, AIS targets the critical components behind AI's exponential growth. Capture potential returns from this transformative technology sector.

Michael Black profil fotoğrafı

Michael Black1 yıl önce

Nice work! This will be a useful dataset!

Srinath Sridhar profil fotoğrafı

Srinath Sridhar1 yıl önce

Thanks, Michael!

Benzer Videolar

⚙️ 404—GEN has released the WORLD'S LARGEST open-source 3D model dataset ⚙️ • 21.5M+ AI-generated 3d models • Open-source and attribution-ready • Larger than all existing 3D datasets combined This is an unmatched scale for Gaussian Splatting research. More details below 🧵 ⬇️

⚙️ 404—GEN has released the WORLD'S LARGEST open-source 3D model dataset ⚙️ • 21.5M+ AI-generated 3d models • Open-source and attribution-ready • Larger than all existing 3D datasets combined This is an unmatched scale for Gaussian Splatting research. More details below 🧵 ⬇️

404

44,735 görüntüleme • 1 yıl önce

To scale GEN-0 capabilities, we are constructing the largest and most diverse real-world manipulation dataset ever built 🌍 including every manipulation task humans can think of – from peeling potatoes, to threading bolts – spanning homes, bakeries, warehouses, factories, & more

To scale GEN-0 capabilities, we are constructing the largest and most diverse real-world manipulation dataset ever built 🌍 including every manipulation task humans can think of – from peeling potatoes, to threading bolts – spanning homes, bakeries, warehouses, factories, & more

Generalist

51,615 görüntüleme • 8 ay önce

Imitation learning has a data scarcity problem. Introducing EgoDex from Apple, the largest and most diverse dataset of dexterous human manipulation to date — 829 hours of egocentric video + paired 3D hand poses across 194 tasks. Now on arxiv: (1/4)

Imitation learning has a data scarcity problem. Introducing EgoDex from Apple, the largest and most diverse dataset of dexterous human manipulation to date — 829 hours of egocentric video + paired 3D hand poses across 194 tasks. Now on arxiv: (1/4)

Ryan Hoque

114,089 görüntüleme • 1 yıl önce

How to harness foundation models for *generalization in the wild* in robot manipulation? Introducing VoxPoser: use LLM+VLM to label affordances and constraints directly in 3D perceptual space for zero-shot robot manipulation in the real world! 🌐 🧵👇

How to harness foundation models for generalization in the wild in robot manipulation? Introducing VoxPoser: use LLM+VLM to label affordances and constraints directly in 3D perceptual space for zero-shot robot manipulation in the real world! 🌐 🧵👇

Wenlong Huang

293,876 görüntüleme • 3 yıl önce

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

49,913 görüntüleme • 2 yıl önce

How can we move beyond static-arm lab setups and learn robot policies in our messy homes? We introduce HoMeR, an imitation learning agent for in-the-wild mobile manipulation. 🧵1/8

How can we move beyond static-arm lab setups and learn robot policies in our messy homes? We introduce HoMeR, an imitation learning agent for in-the-wild mobile manipulation. 🧵1/8

Priya Sundaresan

42,129 görüntüleme • 1 yıl önce

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.

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

122,533 görüntüleme • 2 yıl önce

Biology is always advancing—and so are we. We use scientifically accurate 3D visualizations to bring the most current biological knowledge into the classroom. What you learn reflects today’s science—not last decade’s textbook. Learn more at #biology #3D

Biology is always advancing—and so are we. We use scientifically accurate 3D visualizations to bring the most current biological knowledge into the classroom. What you learn reflects today’s science—not last decade’s textbook. Learn more at #biology #3D

Smart Biology

27,861 görüntüleme • 1 yıl önce

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

41,729 görüntüleme • 1 yıl önce

One of the Top 5 most valuable companies in the world has just acquired a license for Over the Reality 3D mapping dataset to train next-generation vision foundation models. This is a huge milestone for OVER 🧵👇

One of the Top 5 most valuable companies in the world has just acquired a license for Over the Reality 3D mapping dataset to train next-generation vision foundation models. This is a huge milestone for OVER 🧵👇

Over the Reality 🌐

829,911 görüntüleme • 4 ay önce

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

249,572 görüntüleme • 3 yıl önce

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

14,601 görüntüleme • 2 yıl önce

🚀 Our NeurIPS '24 work, Large Spatial Model (LSM), is here! LSM performs semantic 3D reconstruction in just 0.1s, processing unposed data via feed-forward 3D reconstruction. 👉It leverages large-scale 3D datasets with minimal annotations, defining a 3D latent space. We are continuously exploring how this explicit 3D representation can further enhance reasoning and robotic learning. 🔗 Try our online Gradio demo with your own data at #NeurIPS2024 #3DReconstruction

🚀 Our NeurIPS '24 work, Large Spatial Model (LSM), is here! LSM performs semantic 3D reconstruction in just 0.1s, processing unposed data via feed-forward 3D reconstruction. 👉It leverages large-scale 3D datasets with minimal annotations, defining a 3D latent space. We are continuously exploring how this explicit 3D representation can further enhance reasoning and robotic learning. 🔗 Try our online Gradio demo with your own data at #NeurIPS2024 #3DReconstruction

Zhiwen(Aaron) Fan

43,871 görüntüleme • 1 yıl önce

Many works model 3D virtual humans, but how can we create realistic dense crowds? At SIGGRAPH Asia 2024, we will show that solving human-human interactions is key to modeling realistic crowds. project: 🧵1/4

Many works model 3D virtual humans, but how can we create realistic dense crowds? At SIGGRAPH Asia 2024, we will show that solving human-human interactions is key to modeling realistic crowds. project: 🧵1/4

Dan Casas

22,761 görüntüleme • 1 yıl önce

Are we being manipulated without even realizing it, and are we actively participating in the manipulation?

Are we being manipulated without even realizing it, and are we actively participating in the manipulation?

Merissa Hansen

14,223 görüntüleme • 2 ay önce

Can we learn whole-body mobile manipulation directly from human demonstrations? Introducing Whole-Body Mobile Manipulation Interface (HoMMI) Egocentric + UMI, 0 teleop -> bimanual & whole-body manipulation, long-horizon navigation, active perception

Can we learn whole-body mobile manipulation directly from human demonstrations? Introducing Whole-Body Mobile Manipulation Interface (HoMMI) Egocentric + UMI, 0 teleop -> bimanual & whole-body manipulation, long-horizon navigation, active perception

Xiaomeng Xu

77,536 görüntüleme • 3 ay önce

GaVS: 3D-Grounded Video Stabilization via Temporally-Consistent Local Reconstruction and Rendering Contributions: • We reformulate video stabilization as a novel 3D grounded scheme of local reconstruction and rendering. This approach is naturally robust to diverse camera motions and scene dynamics, is temporally consistent, and is capable of full frame stabilization. • We propose a novel test-time optimization for each unstable video. It leverages multi-view dynamics-aware photometric supervision and cross-frame regularization to achieve temporally consistent reconstructions. To avoid frame cropping, we introduce a scene extrapolation module based on video completion. • We provide a 3D-grounded dataset for our task by re-purposing an existing one, and introduce new metrics on sparse and dense reconstruction to evaluate 3D scene consistency. Extensive experiments (quantitative, qualitative, user study) versus image-based and gyro-basedmethods demonstrate the merits of our method.

GaVS: 3D-Grounded Video Stabilization via Temporally-Consistent Local Reconstruction and Rendering Contributions: • We reformulate video stabilization as a novel 3D grounded scheme of local reconstruction and rendering. This approach is naturally robust to diverse camera motions and scene dynamics, is temporally consistent, and is capable of full frame stabilization. • We propose a novel test-time optimization for each unstable video. It leverages multi-view dynamics-aware photometric supervision and cross-frame regularization to achieve temporally consistent reconstructions. To avoid frame cropping, we introduce a scene extrapolation module based on video completion. • We provide a 3D-grounded dataset for our task by re-purposing an existing one, and introduce new metrics on sparse and dense reconstruction to evaluate 3D scene consistency. Extensive experiments (quantitative, qualitative, user study) versus image-based and gyro-basedmethods demonstrate the merits of our method.

MrNeRF

11,638 görüntüleme • 1 yıl önce

🚀 Unitree open-sources UnifoLM-WBT-Dataset — a high-quality real-world humanoid robot whole-body teleoperation (WBT) dataset for open environments. 🥳Publicly available since March 5, 2026, the dataset will continue to receive high-frequency rolling updates. It aims to establish the most comprehensive real-world humanoid robot dataset in terms of scenario coverage, task complexity, and manipulation diversity. 👉 Explore the dataset here:

🚀 Unitree open-sources UnifoLM-WBT-Dataset — a high-quality real-world humanoid robot whole-body teleoperation (WBT) dataset for open environments. 🥳Publicly available since March 5, 2026, the dataset will continue to receive high-frequency rolling updates. It aims to establish the most comprehensive real-world humanoid robot dataset in terms of scenario coverage, task complexity, and manipulation diversity. 👉 Explore the dataset here:

Unitree

5,630,736 görüntüleme • 3 ay önce

Cross-embodied robot policies hold the promise of one policy to control all robots. But how far does transfer go? In new work, we study positive transfer between *manipulation* & *navigation* and show that nav data helps manipulation, and vice versa! 🧵 👇

Cross-embodied robot policies hold the promise of one policy to control all robots. But how far does transfer go? In new work, we study positive transfer between manipulation & navigation and show that nav data helps manipulation, and vice versa! 🧵 👇

Sergey Levine

42,712 görüntüleme • 2 yıl önce

Current 3D generative models are slow and low quality. We present GRM, a large-scale model that reconstructs 3D Gaussians in 0.1s and generates high-quality 3D assets from text or single images in a few seconds. Demo: 1/4

Current 3D generative models are slow and low quality. We present GRM, a large-scale model that reconstructs 3D Gaussians in 0.1s and generates high-quality 3D assets from text or single images in a few seconds. Demo: 1/4

Gordon Wetzstein

19,210 görüntüleme • 2 yıl önce