AI RESEARCH

Unleashing Guidance Without Classifiers for Human-Object Interaction Animation

arXiv CS.CV

ArXi:2603.25734v1 Announce Type: new Generating realistic human-object interaction (HOI) animations remains challenging because it requires jointly modeling dynamic human actions and diverse object geometries. Prior diffusion-based approaches often rely on hand-crafted contact priors or human-imposed kinematic constraints to improve contact quality. We propose LIGHT, a data-driven alternative in which guidance emerges from the denoising pace itself, reducing dependence on manually designed priors.