Introducing HO-Cap: A Capture System and Dataset for 3D Reconstruction and Pose Tracking of Hand-Object Interaction. We built a multi-camera system and a semi-automatic method for annotating the shape and pose of hands and objects Project page:

RT @robot_trainer: Next step in dynamic dexterous grasping from NVIDIA: DextrAH-RGB! No more depth. We’re now consuming RGB stereo pairs,…

@XuYihong666 I think the ICRA website will post all the accepted workshops soon

Finally, the robotics community is catching up with other fields of AI

@vrushankdes Oh, good to know!

Just saw the CVPR reviews. The first thing in my mind is that why CVPR reviewers are so harsh 😂

@highvis_supply You can check this

@chris_j_paxton I am not aware of any robot grasping code that can be pip installed :) We spent much time to build a docker for graspit

We received the GPUs! Our project on Real-to-Sim Force Sensor Modeling is selected by the NVIDIA Academic Grant Program. Thank NVIDIA for donating us 8 RTX 6000 Ada GPUs! #NVIDIAGrant @NVIDIAAIDev @UTDCompSci

@Sriraam_UTD @VibhavGogate @ravi_iitm Congratulations!!

Squid game popup in Shinsegae Seoul. Happy holidays!!

RT @yoonchangsung: I am excited to share that I will be joining Nanyang Technological University (NTU), Singapore, as an Assistant Professo…

RT @Stone_Tao: Yesterday the hyped Genesis simulator released. But it's up to 10x slower than existing GPU sims, not 10-80x faster or 430,0…

@Stone_Tao @chris_j_paxton Great effort to put this up!

In addition to use this dataset to study vision problems, another motivation to is to use the data as human demonstrations for dexterous robot manipulation. These manipulation actions in HO-Cap are very difficult for the current robots, a challenge for future robotic systems