标题： 基于预训练的统一Transformer框架用于全身抓取运动生成 显示英文标题

标题： A Unified Transformer-Based Framework with Pretraining For Whole Body Grasping Motion Generation

摘要： 被接受于ICIP 2025 我们提出了一种基于变压器的全身抓取框架，解决了姿态生成和运动填充问题，实现了真实且稳定的物体交互。 我们的流程包括三个阶段：抓取姿态生成用于全身抓取生成，时间填充用于平滑运动连续性，以及一个 LiftUp 变压器，将下采样的关节细化回高分辨率标记。 为了解决手-物体交互数据的稀缺性，我们引入了一个在大型多样化运动数据集上的高效数据通用预训练阶段，产生了可转移到抓取任务的鲁棒时空表示。 在 GRAB 数据集上的实验表明，我们的方法在连贯性、稳定性和视觉真实性方面优于最先进的基线。 模块化设计还支持轻松适应其他人体运动应用。 显示英文摘要

摘要： Accepted in the ICIP 2025 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.