发表机构
Politecnico di Torino; Consiglio Nazionale delle Ricerche（都灵理工大学; 国家研究委员会（意大利））
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
TransHands是一种与骨干网络无关的迁移学习框架，可将预训练人体运动编码器适配至三维手部姿态估计，在四类运动建模架构上验证了其精度提升、跨域泛化及现实任务适用性。
AI 中文摘要
从二维单目表示中提升三维手部姿态仍然具有挑战性，因为与大量的人体运动数据相比，大规模、多样化的三维标注手部数据集有限。我们通过将从大型人体姿态语料库中学习到的运动表示迁移到手部领域来解决这一限制。我们提出了TransHands，一种与骨干网络无关的迁移学习框架，该框架能让预训练的人体运动编码器有效适配从二维姿态输入进行三维手部姿态估计的任务。TransHands并非从头开始训练手部特定的生物力学模型，而是将两阶段训练与微调策略，以及一个轻量的手部特定输入适配模块相结合，该模块可使手部运动学与为全身运动学习到的表示空间对齐。我们在四种最先进的运动建模架构上评估了TransHands，包括基于Transformer、图和频率域的模型。结果表明，从人体姿态数据中学习到的运动先验可跨架构一致迁移，带来持续的精度提升、强大的跨域泛化能力（尤其是在具有挑战性的第一人称视角场景中），并适用于现实环境中的下游任务。
英文摘要
Lifting 3D hand poses from 2D monocular representations remains challenging due to the limited availability of large-scale, diverse 3D-annotated hand datasets, in contrast to the abundance of human body motion data. We address this limitation by transferring motion representations learned from large body pose corpora to the hand domain. We introduce TransHands, a backbone-agnostic transfer learning framework that enables pre-trained human motion encoders to be effectively adapted for 3D hand pose estimation from 2D pose inputs. Rather than training hand-specific biomechanical models from scratch, TransHands combines a two-stage training and fine-tuning strategy with a lightweight hand-specific input adaptation module that aligns hand kinematics with the representation space learned for full-body motion. We evaluate TransHands across four state-of-the-art motion modeling architectures, including transformer-based, graph-based, and frequency- domain models. Results demonstrate that motion priors learned from body pose data transfer consistently across architectures, yielding consistent accuracy gains, strong cross-domain generalization, particularly in challenging egocentric settings, and applicability for downstream tasks in real-world contexts.
