EPIC-Contact and HOPformer: A Dataset and Model for In-the-Wild Egocentric 3D Hand-Object Pose Estimation
Project page for Towards in-the-wild Egocentric 3D Hand-Object Pose Estimation, introducing EPIC-Contact and HOPformer.
Read the full articleYou might also wanna read
Printing Hand Muscles With Geometry Nodes In Blender 5.2
More of Cartesian Caramel's robotic-style experiments with an organic feel.
SqueakPose Studio, an end-to-end platform for pose estimation and real-time edge-AI deployment
Accurate pose estimation underpins quantitative analysis of behavior, yet many deep learning-based tracking tools remain optimized for offli
SHARE: Pose-Free 3D Gaussian Splatting Framework for Robust Scene Reconstruction
While generalizable 3D Gaussian splatting enables efficient, high-quality rendering of unseen scenes, it heavily depends on precise camera p
arxiv.org·7mo ago
1X unveils tendon-driven hands with 25 degrees of freedom for NEO humanoid robot
1X unveils advanced tendon-driven hands for its NEO humanoid, bringing human-like dexterity closer to real-world robotics.
interestingengineering.com·7d ago
TreeSRNF: A Mathematical Framework for Modeling 3D Tree Geometry and Branching Structure
We introduce a novel mathematical framework for analyzing and generating complex tree-shaped 3D objects, such as botanical trees and plants,
arxiv.org·2d ago
RynnWorld-4D: A Generative 4D World Model for Robotic Manipulation Using RGB-Depth-Flow Representations
Robotic manipulation in the open world requires not only recognizing what a scene looks like, but also anticipating how its 3D structure mov
arxiv.org·8d ago
Comments
Sign in to join the conversation.
No comments yet. Be the first.