Presentation
IntentMotion: Learning Intent-Aware Human Motion from Language in 3D Scene
SessionInvited: Posters
DescriptionIntentMotion is a novel framework that generates human motion in 3D scenes from instructions. We first introduce the Intention-Guided Contact Field (IGCF), which explicitly aligns parsed language roles with spatial contact regions through a hierarchical attention mechanism. IGCF is jointly trained with a diffusion-based motion generator, allowing contact predictions to adapt dynamically through gradient feedback. To improve the controllability and physics-aware motion, we further propose an Intention-Aware Diffusion Model, which decouples the high-level semantic planning from the low-level contact refinement. Contact cues are utilized to guide the synthesis of coarse trajectory, followed by refining detailed pose sequences under IGCF supervision.
Contributors
Event Type
Invited Poster
Poster
TimeMonday, 15 December 20259:00am - 6:00pm HKT
LocationChancellor 1+2, Level 4