JointHOI: 接触マップの同時生成による手と物体のインタラクション生成の強化
JointHOI: Jointly Generating Contact Maps Enhances Hand Object Interaction Generation
テキストから手と物体のインタラクションを生成する際、接触マップを同時生成する単一ステージの拡散モデルを提案し、物理的整合性を向上させた。
著者: Mingyeong Song, Jungbin Cho, Jisoo Kim, Ananya Bal, Kartik Sharma, Youngjae Yu, Laszlo A. Jeni, Junhyug Noh
分類: cs.CV
原文アブストラクト
Text driven hand object interaction (HOI) generation is gaining attention for immersive applications and robotics, yet producing physically plausible interactions remains challenging. Even when individual motions appear natural, small contact errors can cause conspicuous artifacts such as floating and interpenetration. Prior methods mitigate these issues using explicit contact cues or implicit grasp priors, but typically rely on multi stage pipelines and fail to model temporally evolving contact. We present JointHOI, a single stage diffusion framework that jointly generates 3D hand object motion and dynamic, distance based contact maps from text. By treating contact as an auxiliary inner modality, joint generation enables the model to learn contact motion coupling during training. At inference, contact guided sampling enforces consistency between generated contact maps and motion implied geometry, improving temporal stability and reducing penetration and floating. Experiments on GRAB and ARCTIC demonstrate consistent improvements in text adherence and physical plausibility over prior methods.