Video wird geladen...

Video konnte nicht geladen werden

Zur Startseite

Human Archive builds datasets to model sensorimotor intelligence for robotics and world models. HA-Multi is the largest dataset of manual labor tasks aligning egocentric RGB, stereo depth (active IR), tactile gloves, body IMUs, and wrist cameras. Congrats on the launch, Raj Patel, Shloke Patel, Samay Maini, and Rushil Agarwal!

ycombinator's profile picture

Y Combinator

1,660,159 subscribers

111,208 Aufrufe • vor 8 Monaten •via X (Twitter)

KunstBildungWissenschaft & Technologie
LIVE

Anya Rossi• Live Now

Private livecam show

34 Kommentare

Profilbild von Runtime
Runtimevor 8 Monaten

Onwards and upwards!

Profilbild von Panda Hodler (YC Intern)
Panda Hodler (YC Intern)vor 8 Monaten

This seems to equip robots with "human-level tactile and visual nerves." The team's approach is very interesting i think😆

Profilbild von WildPinesAI
WildPinesAIvor 8 Monaten

tactile force maps aligned with vision is the missing dataset every robotics foundation model is starving for

Profilbild von Samay Maini
Samay Mainivor 8 Monaten

let’s archive the world for embodied intelligence!

Profilbild von Kai
Kaivor 8 Monaten

This stack is wild, egocentric video plus tactile plus IMU in one dataset is exactly what makes sim to real less brittle. Fine tuning policies from this should beat pure vision only sets.

Profilbild von Maahir Sachdev
Maahir Sachdevvor 8 Monaten

congrats champ

Profilbild von Kyriakos
Kyriakosvor 8 Monaten

AI needs real world datasets

Profilbild von Manideep
Manideepvor 8 Monaten

this is goated startup in this batch

Profilbild von Jai Bhatia
Jai Bhatiavor 8 Monaten

Congrats boys!

Profilbild von Skyler Chan
Skyler Chanvor 8 Monaten

congrats raj!

Profilbild von BTCaveman.
BTCaveman.vor 8 Monaten

Lfg boys! Kill it ! Proud to see my Indians together like this

Profilbild von The Humanoid Hub
The Humanoid Hubvor 8 Monaten

Models are hungry!!

Profilbild von Mohd Tanveer
Mohd Tanveervor 8 Monaten

Exciting step forward for embodied AI and robotics. Congrats to the team! 🚀

Profilbild von Chain Alpha
Chain Alphavor 8 Monaten

Congrats!

Profilbild von Rushil Agarwal
Rushil Agarwalvor 8 Monaten

Super excited

Profilbild von sreekar nagulapalli
sreekar nagulapallivor 8 Monaten

let’s goooo

Profilbild von Rithvik
Rithvikvor 8 Monaten

Goats

Profilbild von Sanjay Adhikesaven
Sanjay Adhikesavenvor 8 Monaten

congrats!

Profilbild von Abhishek Vadapalli
Abhishek Vadapallivor 8 Monaten

Congrats @babugi28!!

Profilbild von parag parikh
parag parikhvor 8 Monaten

Congratulations and Goodluck ...

Profilbild von Chawit
Chawitvor 8 Monaten

looks amazing!

Profilbild von vishnu manoj
vishnu manojvor 8 Monaten

lfgg🚀

Profilbild von Testimony | Product Designer
Testimony | Product Designervor 8 Monaten

put enough sensors on a human doing manual labor and suddenly you have the most expensive dishwashing video ever recorded. congrats on the launch

Profilbild von justin wang
justin wangvor 8 Monaten

congrats on the launch raj!!

Profilbild von Shamim Hossain
Shamim Hossainvor 8 Monaten

Congratulations on the launch!

Profilbild von interstellar
interstellarvor 8 Monaten

Great !

Profilbild von Mohamed Anis
Mohamed Anisvor 8 Monaten

Excited to see how this enables the next generation of foundation models for physical AI.

Profilbild von The Daily_Ai
The Daily_Aivor 8 Monaten

Exciting stuff! The integration of all those data types will really push robotics forward. Can't wait to see what comes next!

Profilbild von Rayan
Rayanvor 8 Monaten

Congrats !

Profilbild von Ali Taha Brown
Ali Taha Brownvor 8 Monaten

Congrats team

Profilbild von Neel Sharma
Neel Sharmavor 8 Monaten

BANG

Profilbild von Keshav Agarwal
Keshav Agarwalvor 8 Monaten

We have build some apps that we would soon be launching on X and would YC to have a look if they find interesting

Profilbild von Veer Sahasi
Veer Sahasivor 8 Monaten

Awesome!!

Profilbild von Shrinandan Narayanan
Shrinandan Narayananvor 8 Monaten

Congrats guys!

Ähnliche Videos

Ropedia Xperience-10M is out on Hugging Face a large-scale egocentric multimodal dataset of human experience for embodied AI, robotics, world models, and spatial intelligence It contains 10 million experiences (interaction) and 10,000 hours of synchronized first-person recordings with six video streams, audio, stereo depth, camera pose, hand mocap, full-body mocap, IMU, and hierarchical language annotations dataset:
1:32

Ropedia Xperience-10M is out on Hugging Face a large-scale egocentric multimodal dataset of human experience for embodied AI, robotics, world models, and spatial intelligence It contains 10 million experiences (interaction) and 10,000 hours of synchronized first-person recordings with six video streams, audio, stereo depth, camera pose, hand mocap, full-body mocap, IMU, and hierarchical language annotations dataset:

AK

10,621 Aufrufe • vor 7 Monaten

SAVA Robotics (SuperBee) builds robot operators for sheet metal machines, addressing the critical labor shortage in American manufacturing. Congrats on the launch, Jakob Knudsen, @_alessiotoniolo, and Vedic Patel!
1:06

SAVA Robotics (SuperBee) builds robot operators for sheet metal machines, addressing the critical labor shortage in American manufacturing. Congrats on the launch, Jakob Knudsen, @_alessiotoniolo, and Vedic Patel!

Y Combinator

24,418 Aufrufe • vor 1 Jahr

Lancey (Lancey) is the multiplayer coding agent that builds what your customers want. Lancey scans your customer channels, builds an understanding of your codebase, and one-shots PRs. All in the background, without human prompting. Congrats on the launch, adi patel & Abhi Patel 🦭!
1:08

Lancey (Lancey) is the multiplayer coding agent that builds what your customers want. Lancey scans your customer channels, builds an understanding of your codebase, and one-shots PRs. All in the background, without human prompting. Congrats on the launch, adi patel & Abhi Patel 🦭!

Y Combinator

29,027 Aufrufe • vor 11 Monaten

I tested out the egocentric headset with wrist camera + UMI gripper from Maniformer. Maniformer is the robotics data company incubated by AGIBOT . Now it has 2 product lines for data collection: egocentric headset with wrist cameras + UMI gripper. The MEgo View comes with a 5-camera headset + 2 wrist cameras, 300 degree view, global shutter, 2-hour battery life with hot swapping. The MEgo Gripper comes with 3 cameras, optional 3D tactile, global shutter, 200 degree fisheye. For both devices, you can upload the data by Wifi, USB or SD card. The data output includes 7-camera RGB image, depth info, IMU, trajectory and audio. On top of these, the gripper provides tactile info, gripper distance and angle as well. The app expands multiple use cases. It is not only for enterprises to sync the equipments and check the video stream in real time, but also for consumers to claim the tasks and earn earn real cash. Check the video for details. DM is open.
1:40

I tested out the egocentric headset with wrist camera + UMI gripper from Maniformer. Maniformer is the robotics data company incubated by AGIBOT . Now it has 2 product lines for data collection: egocentric headset with wrist cameras + UMI gripper. The MEgo View comes with a 5-camera headset + 2 wrist cameras, 300 degree view, global shutter, 2-hour battery life with hot swapping. The MEgo Gripper comes with 3 cameras, optional 3D tactile, global shutter, 200 degree fisheye. For both devices, you can upload the data by Wifi, USB or SD card. The data output includes 7-camera RGB image, depth info, IMU, trajectory and audio. On top of these, the gripper provides tactile info, gripper distance and angle as well. The app expands multiple use cases. It is not only for enterprises to sync the equipments and check the video stream in real time, but also for consumers to claim the tasks and earn earn real cash. Check the video for details. DM is open.

ClaraChengGo

13,758 Aufrufe • vor 2 Monaten

Sortex: our data quality platform built to search and filter the world's largest egocentric dataset. Across 50+ environments and 20k+ tasks, it uses an in-house model and evaluation harness to score each clip's usability, selecting for specific training objectives by: → Narrating tasks and steps → Checking hand and action visibility → Comparing against the rest of the corpus We also tested Sortex on popular open datasets and found they differ widely in quality and coverage.
0:28

Sortex: our data quality platform built to search and filter the world's largest egocentric dataset. Across 50+ environments and 20k+ tasks, it uses an in-house model and evaluation harness to score each clip's usability, selecting for specific training objectives by: → Narrating tasks and steps → Checking hand and action visibility → Comparing against the rest of the corpus We also tested Sortex on popular open datasets and found they differ widely in quality and coverage.

Midcentury

16,368 Aufrufe • vor 8 Tagen

introducing Egocentric-1M. the largest egocentric video dataset in the world, and our next step in building the internet for physical AI.
1:02

introducing Egocentric-1M. the largest egocentric video dataset in the world, and our next step in building the internet for physical AI.

Eddy Xu

340,565 Aufrufe • vor 7 Monaten

ReViV: Reconstructing the Viewer and the View in 4D from Monocular Egocentric Video(ECCV2026) ReViV reconstructs viewer-centric human motion (body, hand, and gaze) and view-centric scene geometry (camera and depth) from a single egocentric RGB video in a unified feed-forward model. For visualization, the initial camera pose and camera intrinsics are estimated with GeoCalib.
0:54

ReViV: Reconstructing the Viewer and the View in 4D from Monocular Egocentric Video(ECCV2026) ReViV reconstructs viewer-centric human motion (body, hand, and gaze) and view-centric scene geometry (camera and depth) from a single egocentric RGB video in a unified feed-forward model. For visualization, the initial camera pose and camera intrinsics are estimated with GeoCalib.

Ryohei Sasaki@engineer

15,096 Aufrufe • vor 2 Monaten

Intelligence Factory is building human intelligence for robots. They train general-purpose manipulation models on human demonstration data (vision, action, and touch), then deploy them in warehouses, grocery stores, and data centers. Congrats on the launch, Yash and Jalaj!
1:40

Intelligence Factory is building human intelligence for robots. They train general-purpose manipulation models on human demonstration data (vision, action, and touch), then deploy them in warehouses, grocery stores, and data centers. Congrats on the launch, Yash and Jalaj!

Y Combinator

44,842 Aufrufe • vor 5 Monaten

Presenting research from Berkeley AI Research Humanoid Intelligence Center. DexTacWAM: A Visuo-Tactile World-Action Model for Dexterous Manipulation.🖐️🤖 Dexterous manipulation requires touch, yet multi-finger tactile data remain scarce and expensive to collect at scale. Through continual vision-to-touch learning, DexTacWAM adapts a pretrained video world model into a visuo-tactile world model for predictive multi-finger contact modeling and action generation. Across six contact-rich dexterous manipulation tasks, DexTacWAM achieves the highest score on every task, averaging 70.6 vs. 38.0 for the strongest baseline. 🔬 Why not simply inject tactile features into the action policy? With the same multi-finger tactile encoder, policy architecture, and training procedure, replacing the tactile world-model latent with direct tactile features drops the 4-task mean from 74.7 to 26.6. Takeaway: the benefit does not come simply from providing tactile observations to the policy, but from making multi-finger contact evolution part of the predicted world state. All code, model weights, and datasets are now open-sourced! 🌐 Project: 📄 Paper: 💻 Code: 🤗 Weights&Data: Author List: Haoran Yuan✈️Corl, Zekai Wang, Boning Shao Haoran Lu, trevordarrell, Ismini Lourentzou, Wei ZHAN
2:24

Presenting research from Berkeley AI Research Humanoid Intelligence Center. DexTacWAM: A Visuo-Tactile World-Action Model for Dexterous Manipulation.🖐️🤖 Dexterous manipulation requires touch, yet multi-finger tactile data remain scarce and expensive to collect at scale. Through continual vision-to-touch learning, DexTacWAM adapts a pretrained video world model into a visuo-tactile world model for predictive multi-finger contact modeling and action generation. Across six contact-rich dexterous manipulation tasks, DexTacWAM achieves the highest score on every task, averaging 70.6 vs. 38.0 for the strongest baseline. 🔬 Why not simply inject tactile features into the action policy? With the same multi-finger tactile encoder, policy architecture, and training procedure, replacing the tactile world-model latent with direct tactile features drops the 4-task mean from 74.7 to 26.6. Takeaway: the benefit does not come simply from providing tactile observations to the policy, but from making multi-finger contact evolution part of the predicted world state. All code, model weights, and datasets are now open-sourced! 🌐 Project: 📄 Paper: 💻 Code: 🤗 Weights&Data: Author List: Haoran Yuan✈️Corl, Zekai Wang, Boning Shao Haoran Lu, trevordarrell, Ismini Lourentzou, Wei ZHAN

Berkeley AI Research

113,791 Aufrufe • vor 1 Monat

.One Robot builds world model-based simulations that are realistic to see and realistic to interact with, so robotics teams can train and evaluate VLAs without being bottlenecked by robot time. Congrats on the launch, Hemanth Sarabu and Elton Bear!
1:40

.One Robot builds world model-based simulations that are realistic to see and realistic to interact with, so robotics teams can train and evaluate VLAs without being bottlenecked by robot time. Congrats on the launch, Hemanth Sarabu and Elton Bear!

Y Combinator

26,020 Aufrufe • vor 8 Monaten

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)
0:27

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

114,370 Aufrufe • vor 1 Jahr

Training robot hands at scale! 🪬 Lightwheel released EgoSuite-Open100K, a 100,000-hour open dataset of egocentric video with hand and body pose annotations. Everything is available on Hugging Face. Multiple variants for different needs. → Head-view only for hand-centric tasks. → Wrist-view for close-range contact and grasping detail. → Full-body pose variants for whole-body context. → Raw video variants without annotations for lightweight inspection. 15,000+ distinct tasks across 15,000+ different scenes. Egocentric data is gold for imitation learning. Show a robot how humans actually manipulate things from the perspective humans have, from their eyes, from the wrist. Hand pose annotations transfer directly to robot hands. Wrist-camera view shows contact dynamics most robots need to learn. Multiple data formats, LeRobot v3 and MCAP, so researchers can use whatever their pipeline expects. Semantic annotations at the subtask level, not just raw video. Congrats Steve Xie, and team! 🦾 Find it on HF: ~~ ♻ Join the weekly robotics newsletter, and never miss any news →
0:30

Training robot hands at scale! 🪬 Lightwheel released EgoSuite-Open100K, a 100,000-hour open dataset of egocentric video with hand and body pose annotations. Everything is available on Hugging Face. Multiple variants for different needs. → Head-view only for hand-centric tasks. → Wrist-view for close-range contact and grasping detail. → Full-body pose variants for whole-body context. → Raw video variants without annotations for lightweight inspection. 15,000+ distinct tasks across 15,000+ different scenes. Egocentric data is gold for imitation learning. Show a robot how humans actually manipulate things from the perspective humans have, from their eyes, from the wrist. Hand pose annotations transfer directly to robot hands. Wrist-camera view shows contact dynamics most robots need to learn. Multiple data formats, LeRobot v3 and MCAP, so researchers can use whatever their pipeline expects. Semantic annotations at the subtask level, not just raw video. Congrats Steve Xie, and team! 🦾 Find it on HF: ~~ ♻ Join the weekly robotics newsletter, and never miss any news →

Lukas Ziegler

13,421 Aufrufe • vor 2 Monaten

The largest fully annotated open egocentric human dataset. Today we're open-sourcing EgoSuite-Open100K with Hugging Face : 100,000 hours of egocentric human data, free for anyone to use. Physical AI has a scaling law of its own now, and its input is human data. That part is settled. What the field still needs is a shared foundation to build on. 15,000+ tasks. 15,000+ real scenes, from factory floors to retail backrooms. Hand pose, body pose and subtask-level semantics, with wrist camera coverage on part of the set. Licensed for commercial training, not research-only. We build the data infrastructure for Physical AI. Open100K is the first public layer of it. The first 10,000 hours are live now, with the rest rolling out in stages.
1:18

The largest fully annotated open egocentric human dataset. Today we're open-sourcing EgoSuite-Open100K with Hugging Face : 100,000 hours of egocentric human data, free for anyone to use. Physical AI has a scaling law of its own now, and its input is human data. That part is settled. What the field still needs is a shared foundation to build on. 15,000+ tasks. 15,000+ real scenes, from factory floors to retail backrooms. Hand pose, body pose and subtask-level semantics, with wrist camera coverage on part of the set. Licensed for commercial training, not research-only. We build the data infrastructure for Physical AI. Open100K is the first public layer of it. The first 10,000 hours are live now, with the rest rolling out in stages.

Lightwheel

76,680 Aufrufe • vor 2 Monaten

🔥 JUST IN: Open-source robotics dataset from 100% real-world scenarios! 🤯 Chinese robotics company AGIBOT just released AGIBOT WORLD 2026, an open-source dataset systematically covering key embodied AI research directions. Built entirely from real-world environments: commercial spaces, and homes. Collected using AGIBOT G2 robots in free-form collection mode, providing structured, accurately annotated, high-quality data. Digital twin technology creates 1:1 scale replicas in simulation matching the real environments. Both real-world and simulation data are open-sourced. The AGIBOT G2 platform collects multiple data types simultaneously: RGB(D) cameras, tactile sensors, force sensors, LiDAR, IMU, and full-body joint states. Whole-body control coordinates arms, waist, and hands for complex tasks. First-person teleoperation lets operators control the robot from its perspective. The tasks covered are fine-grained manipulation, ultra-long-horizon tasks, spatial navigation, dual-arm coordination, and multi-agent/human-robot collaboration. The dataset includes error-recovery trajectories with annotations. Most datasets only show successful demonstrations. AGIBOT includes failures and how the robot recovers, teaching models how to handle mistakes. After collection, data is tested through policy training and real-robot deployment to ensure quality. Then processed through industrial quality control with multiple screening and cleaning rounds. Making it open-source accelerates embodied AI research by giving researchers access to high-quality real-world robot data at scale. 🇨🇳 Learn more here: ~~ ♻️ Join the weekly robotics newsletter, and never miss any news →
0:26

🔥 JUST IN: Open-source robotics dataset from 100% real-world scenarios! 🤯 Chinese robotics company AGIBOT just released AGIBOT WORLD 2026, an open-source dataset systematically covering key embodied AI research directions. Built entirely from real-world environments: commercial spaces, and homes. Collected using AGIBOT G2 robots in free-form collection mode, providing structured, accurately annotated, high-quality data. Digital twin technology creates 1:1 scale replicas in simulation matching the real environments. Both real-world and simulation data are open-sourced. The AGIBOT G2 platform collects multiple data types simultaneously: RGB(D) cameras, tactile sensors, force sensors, LiDAR, IMU, and full-body joint states. Whole-body control coordinates arms, waist, and hands for complex tasks. First-person teleoperation lets operators control the robot from its perspective. The tasks covered are fine-grained manipulation, ultra-long-horizon tasks, spatial navigation, dual-arm coordination, and multi-agent/human-robot collaboration. The dataset includes error-recovery trajectories with annotations. Most datasets only show successful demonstrations. AGIBOT includes failures and how the robot recovers, teaching models how to handle mistakes. After collection, data is tested through policy training and real-robot deployment to ensure quality. Then processed through industrial quality control with multiple screening and cleaning rounds. Making it open-source accelerates embodied AI research by giving researchers access to high-quality real-world robot data at scale. 🇨🇳 Learn more here: ~~ ♻️ Join the weekly robotics newsletter, and never miss any news →

Lukas Ziegler

40,583 Aufrufe • vor 7 Monaten

🤖Verne Robotics builds AI software for robot arms to learn new skills in hours (their AI model is SOTA), making it easy for any company to adopt automation. Congrats on the launch, Neil Nie and Aditya Jha!
1:00

🤖Verne Robotics builds AI software for robot arms to learn new skills in hours (their AI model is SOTA), making it easy for any company to adopt automation. Congrats on the launch, Neil Nie and Aditya Jha!

Y Combinator

74,550 Aufrufe • vor 1 Jahr

How do you scale 2 million hours of ego data without sacrificing quality? Earlier this week, we revealed the world’s largest egocentric dataset. Our frontier pipeline has also turned it into the most labeled, annotated, and human QA’ed robotics ego dataset in the world. We’ve focused on some of the hardest problems in computer vision and ego data to ensure every clip contains SOTA action supervision directly helpful for training dexterous manipulation.
0:21

How do you scale 2 million hours of ego data without sacrificing quality? Earlier this week, we revealed the world’s largest egocentric dataset. Our frontier pipeline has also turned it into the most labeled, annotated, and human QA’ed robotics ego dataset in the world. We’ve focused on some of the hardest problems in computer vision and ego data to ensure every clip contains SOTA action supervision directly helpful for training dexterous manipulation.

Midcentury

10,802 Aufrufe • vor 1 Monat

Stereo depth models usually force a tradeoff. 📌 Paper + Code Either strong zero-shot generalization or real-time speed. Fast-FoundationStereo closes that gap. The model accelerates FoundationStereo by more than 10× while keeping comparable depth quality, making real-time stereo matching practical for robotics and XR. On an RTX 3090, it produces dense metric depth maps and 3D point clouds in real time, outperforming existing real-time stereo approaches and even challenging some heavier zero-shot models. The key idea is a divide-and-conquer architecture that removes bottlenecks in common stereo matching components while preserving the strengths of the original teacher model. Training also tackles a major constraint in stereo vision: the lack of ground-truth metric depth data. The team built an automatic data curation pipeline that generates pseudo-labels from internet-scale stereo imagery using the Stereo4D dataset. Result: a real-time stereo foundation model with strong zero-shot performance and practical runtime speed. Code, pretrained weights, and pseudo-labeled stereo data will be released. Thanks for sharing, Bowen Wen! 📍Paper: Code: Project: ——- Weekly robotics and AI insights. Subscribe free:
0:25

Stereo depth models usually force a tradeoff. 📌 Paper + Code Either strong zero-shot generalization or real-time speed. Fast-FoundationStereo closes that gap. The model accelerates FoundationStereo by more than 10× while keeping comparable depth quality, making real-time stereo matching practical for robotics and XR. On an RTX 3090, it produces dense metric depth maps and 3D point clouds in real time, outperforming existing real-time stereo approaches and even challenging some heavier zero-shot models. The key idea is a divide-and-conquer architecture that removes bottlenecks in common stereo matching components while preserving the strengths of the original teacher model. Training also tackles a major constraint in stereo vision: the lack of ground-truth metric depth data. The team built an automatic data curation pipeline that generates pseudo-labels from internet-scale stereo imagery using the Stereo4D dataset. Result: a real-time stereo foundation model with strong zero-shot performance and practical runtime speed. Code, pretrained weights, and pseudo-labeled stereo data will be released. Thanks for sharing, Bowen Wen! 📍Paper: Code: Project: ——- Weekly robotics and AI insights. Subscribe free:

Ilir Aliu

11,914 Aufrufe • vor 2 Monaten

Cortex AI (CortexAI) produces the world's most diverse egocentric and robot dataset, captured in real workplace environments. Leading research labs use Cortex AI to collect data and deploy robotics foundation models in real-world settings.
0:36

Cortex AI (CortexAI) produces the world's most diverse egocentric and robot dataset, captured in real workplace environments. Leading research labs use Cortex AI to collect data and deploy robotics foundation models in real-world settings.

Y Combinator

16,647 Aufrufe • vor 11 Monaten

Hub (@hubxyz) provides real-world training data to frontier AI labs and robotics. Human labor is half of global GDP. Almost none of it has ever been recorded. Hub opens access to it through a global network of contributors capturing hard-to-access data. Congrats on the launch, Armin and Tim!
0:50

Hub (@hubxyz) provides real-world training data to frontier AI labs and robotics. Human labor is half of global GDP. Almost none of it has ever been recorded. Hub opens access to it through a global network of contributors capturing hard-to-access data. Congrats on the launch, Armin and Tim!

Y Combinator

106,174 Aufrufe • vor 4 Monaten

The BEDLAM2.0 dataset (B2) is here, just in time to train your 3D human pose and shape estimation methods for CVPR. B2 goes beyond BEDLAM (B1) to include widely varied and natural camera motions and fields of view, more diverse body shapes, strand-based hair, more garments, shoes, more body motions, and more 3D scenes. Compared with B1, training on B2 produces more accurate 3D human pose, resulting in SOTA accuracy, particularly for estimates in world coordinates. B2 lets you jointly train camera motion and human motion regressors, and we also provide depth maps. Check out data, code, dataset statistics, and much more. BEDLAM2.0 will appear in the 2025 NeurIPS Datasets and Benchmarks Track. Joint work with Joachim Tesch, Giorgio Becherini, Prerana Achar, Anastasios Yiannakidis, Muhammed Kocabas, Priyanka Patel.
0:30

The BEDLAM2.0 dataset (B2) is here, just in time to train your 3D human pose and shape estimation methods for CVPR. B2 goes beyond BEDLAM (B1) to include widely varied and natural camera motions and fields of view, more diverse body shapes, strand-based hair, more garments, shoes, more body motions, and more 3D scenes. Compared with B1, training on B2 produces more accurate 3D human pose, resulting in SOTA accuracy, particularly for estimates in world coordinates. B2 lets you jointly train camera motion and human motion regressors, and we also provide depth maps. Check out data, code, dataset statistics, and much more. BEDLAM2.0 will appear in the 2025 NeurIPS Datasets and Benchmarks Track. Joint work with Joachim Tesch, Giorgio Becherini, Prerana Achar, Anastasios Yiannakidis, Muhammed Kocabas, Priyanka Patel.

Michael Black

27,714 Aufrufe • vor 1 Jahr