5 papers
FlexiAvatar: Unified 3D Gaussian Human Avatars Under Arbitrary Body Visibility
Yihalem Yimolal Tiruneh, Muhammad Salman Ali, Uyoung Jeong +5
Reconstructing animatable 3D human avatars from monocular video is a fundamental problem in computer vision with broad applications in AR/VR and digital content creation. Existing…
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…
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…
HandVQA: Diagnosing and Improving Fine-Grained Spatial Reasoning about Hands in Vision-Language Models
MD Khalequzzaman Chowdhury Sayem, Mubarrat Tajoar Chowdhury, Yihalem Yimolal Tiruneh +4
Understanding the fine-grained articulation of human hands is critical in high-stakes settings such as robot-assisted surgery, chip manufacturing, and AR/VR-based human-AI interact…
PoseBH: Prototypical Multi-Dataset Training Beyond Human Pose Estimation
Uyoung Jeong, Jonathan Freer, Seungryul Baek +2
We study multi-dataset training (MDT) for pose estimation, where skeletal heterogeneity presents a unique challenge that existing methods have yet to address. In traditional domain…