6 papers
Multi-THuMBS: Multi-person Tracking of 3D Human Meshes Beyond Video Shots
Jeongwan On, Muhammad Salman Ali, Muneeb A. Khan +6
Tracking multi-person 3D human meshes from in-the-wild videos is a highly challenging problem due to complex interactions, frequent occlusions, and severe truncation inherent in un…
AISPO: Enhancing Depth Reliability for Robotic Manipulation of Non-Lambertian Objects via Affine-Invariant Shape Prior
Zhiming Chen, Linfang Zheng, Kun Zhang +4
Reliable depth perception is critical for robotic manipulation, especially for non-Lambertian objects such as transparent or highly specular surfaces, where raw depth measurements…
THOM: Generating Physically Plausible Hand-Object Meshes From Text
Uyoung Jeong, Yihalem Yimolal Tiruneh, Hyung Jin Chang +2
Generating photorealistic 3D hand-object interactions (HOIs) from text is important for applications like robotic grasping and AR/VR content creation. In practice, however, achievi…
GraspALL: Adaptive Structural Compensation from Illumination Variation for Robotic Garment Grasping in Any Low-Light Conditions
Haifeng Zhong, Wenshuo Han, Zhouyu Wang +10
Achieving accurate garment grasping under dynamically changing illumination is crucial for all-day operation of service robots.However, the reduced illumination in low-light scenes…
High-Resolution Spatiotemporal Modeling with Global-Local State Space Models for Video-Based Human Pose Estimation
Runyang Feng, Hyung Jin Chang, Tze Ho Elden Tse +3
Modeling high-resolution spatiotemporal representations, including both global dynamic contexts (e.g., holistic human motion tendencies) and local motion details (e.g., high-freque…
Collaborative Learning for 3D Hand-Object Reconstruction and Compositional Action Recognition from Egocentric RGB Videos Using Superquadrics
Tze Ho Elden Tse, Runyang Feng, Linfang Zheng +5
With the availability of egocentric 3D hand-object interaction datasets, there is increasing interest in developing unified models for hand-object pose estimation and action recogn…