6 papers
AGILE: Hand-Object Interaction Reconstruction from Video via Agentic Generation
Jin-Chuan Shi, Binhong Ye, Tao Liu +6
Reconstructing dynamic hand-object interactions from monocular videos is critical for dexterous manipulation data collection and creating realistic digital twins for robotics and V…
Dream4D: Lifting Camera-Controlled I2V towards Spatiotemporally Consistent 4D Generation
Xiaoyan Liu, Kangrui Li, Yuehao Song +1
The synthesis of spatiotemporally coherent 4D content presents fundamental challenges in computer vision, requiring simultaneous modeling of high-fidelity spatial representations a…
Interacted Object Grounding in Spatio-Temporal Human-Object Interactions
Xiaoyang Liu, Boran Wen, Xinpeng Liu +6
Spatio-temporal Human-Object Interaction (ST-HOI) understanding aims at detecting HOIs from videos, which is crucial for activity understanding. However, existing whole-body-object…
MotionRL: Align Text-to-Motion Generation to Human Preferences with Multi-Reward Reinforcement Learning
Xiaoyang Liu, Yunyao Mao, Wengang Zhou +1
We introduce MotionRL, the first approach to utilize Multi-Reward Reinforcement Learning (RL) for optimizing text-to-motion generation tasks and aligning them with human preference…
PriorMapNet: Enhancing Online Vectorized HD Map Construction with Priors
Rongxuan Wang, Xin Lu, Xiaoyang Liu +3
Online vectorized High-Definition (HD) map construction is crucial for subsequent prediction and planning tasks in autonomous driving. Following MapTR paradigm, recent works have m…
Learning Generalizable Human Motion Generator with Reinforcement Learning
Yunyao Mao, Xiaoyang Liu, Wengang Zhou +2
Text-driven human motion generation, as one of the vital tasks in computer-aided content creation, has recently attracted increasing attention. While pioneering research has largel…