4DHands: Reconstructing Interactive Hands in 4D with Transformers

Dixuan Lin1,2, Yuxiang Zhang2, Mengcheng Li2, Yebin Liu2,
Wei Jing3, Qi Yan3, Qianying Wang3*, Hongwen Zhang1*

1Beijing Normal University, 2Tsinghua University, 3 Lenovo

4DHands can robustly recover interactive hand meshes and their relative movement from monocular inputs.

Results - Monocular Video Input

4DHands outperforms other interactive hand reconstruction methods in real-world videos.

Results - Single Image Input

4DHands has robust performance in complex cases.

Results - Complex Interactions

4DHands has robust performance in complex cases.

Results - Multi-Cameras

4DHands can handle highly occluded cases when applied to multi-view tasks.