activity
20242026
collaborators

13 papers

cs.CV2026

DETRAM: End-to-end DEtection, Tracking and Recovery of HumAn Meshes

Chunggi Lee, Seonwook Park, Wanhua Li +2

In the task of human mesh recovery (HMR), multi-person scenes are particularly difficult to handle due to the many entities that appear and occlusions between them over time. In pa…

cs.RO2026

GRAIL: Generating Humanoid Loco-Manipulation from 3D Assets and Video Priors

Tianyi Xie, Haotian Zhang, Jinhyung Park +17

Scaling humanoid loco-manipulation requires robot-compatible demonstrations across diverse objects, whole-body motions, and scene geometries, but teleoperation and motion capture a…

cs.RO2026

SONIC: Supersizing Motion Tracking for Natural Humanoid Whole-Body Control

Zhengyi Luo, Ye Yuan, Tingwu Wang +26

Despite the rise of billion-parameter foundation models trained across thousands of graphical processing units (GPUs), similar scaling gains have not been shown for humanoid contro…

cs.GR2026

D-Rex : Diffusion Rendering for Relightable Expressive Avatars

Timo Teufel, Xilong Zhou, Umar Iqbal +4

We present D-Rex, a person-specific framework for photorealistic, relightable, expressive, and animatable full-body human avatars with free-viewpoint rendering. Existing methods fo…

cs.CV2026

SOMA: Unifying Parametric Human Body Models

Jun Saito, Jiefeng Li, Michael de Ruyter +12

Parametric human body models are foundational to human reconstruction, animation, and simulation, yet they remain mutually incompatible: SMPL, SMPL-X, MHR, Anny, and related models…

cs.CV2026

Kimodo: Scaling Controllable Human Motion Generation

Davis Rempe, Mathis Petrovich, Ye Yuan +21

High-quality human motion data is becoming increasingly important for applications in robotics, simulation, and entertainment. Recent generative models offer a potential data sourc…