3 papers
cs.CV2026
Controllable Text-to-Motion Generation via Modular Body-Part Phase Control
Minyue Dai, Ke Fan, Anyi Rao +2
Text-to-motion (T2M) generation is becoming a practical tool for animation and interactive avatars. However, modifying specific body parts while maintaining overall motion coherenc…
cs.RO2025
DHAGrasp: Synthesizing Affordance-Aware Dual-Hand Grasps with Text Instructions
Quanzhou Li, Zhonghua Wu, Jingbo Wang +2
Learning to generate dual-hand grasps that respect object semantics is essential for robust hand-object interaction but remains largely underexplored due to dataset scarcity. Exist…
cs.CV2024
PACER+: On-Demand Pedestrian Animation Controller in Driving Scenarios
Jingbo Wang, Zhengyi Luo, Ye Yuan +2
We address the challenge of content diversity and controllability in pedestrian simulation for driving scenarios. Recent pedestrian animation frameworks have a significant limitati…