A Unified Transformer-Based Framework with Pretraining for Whole Body Grasping Motion Generation
Year: 2025
Type: conference-paper
Abstract: We present a novel transformer-based framework for whole-body grasping that addresses both pose generation and motion infilling, enabling realistic and stable object interactions. Our pipeline comprises three stages: Grasp Pose Generation for full-body grasp generation, Temporal Infilling for smooth motion continuity, and a LiftUp Transformer that refines downsampled joints back to high-resolution markers. To overcome the scarcity of hand-object interaction data, we introduce a data-efficient Generalized Pretraining stage on large, diverse motion datasets, yielding robust spatio-temporal representations transferable to grasping tasks. Experiments on the GRAB dataset show that our method outperforms state-of-the-art baselines in terms of coherence, stability, and visual realism. The modular design also supports easy adaptation to other human-motion applications. The code can be seen$\color{Purple}{\text{here}}$.
Authors: Edward Effendy, Kuan-Wei Tseng, Rei Kawakami
Institution: Institute of Science Tokyo
Language: English
Topic: Human Motion and Animation
Subfield: Control and Systems Engineering
Field: Engineering
Domain: Physical Sciences
Open Access status: green
Award: 深層生成モデルを活用した構成的なパターン認識・理解
OpenAlex ID: W4413278122