ACR: Attention Collaboration-based Regressor for Arbitrary Two-Hand Reconstruction

Yu, Z.; Haung, S.; Fang, C.; Breckon, T.P.; Wang, J.

Abstract

Reconstructing two hands from monocular RGB images is challenging due to frequent occlusion and mutual confusion. Existing methods mainly learn an entangled representation to encode two interacting hands, which are incredibly fragile to impaired interaction, such as truncated hands, separate hands, or external occlusion. This paper presents ACR (Attention Collaboration-based Regressor), which makes the first attempt to reconstruct hands in arbitrary scenarios. To achieve this, ACR explicitly mitigates interdependencies between hands and between parts by leveraging center and part-based attention for feature extraction. However, reducing interdependence helps release the input constraint while weakening the mutual reasoning about reconstructing the interacting hands. Thus, based on center attention, ACR also learns cross-hand prior that handle the interacting hands better. We evaluate our method on various types of hand reconstruction datasets. Our method significantly outperforms the best interacting-hand approaches on the InterHand2.6M dataset while yielding comparable performance with the state-ofthe-art single-hand methods on the FreiHand dataset. More qualitative results on in-the-wild and hand-object interaction datasets and web images/videos further demonstrate the effectiveness of our approach for arbitrary hand reconstruction.

Citation

Yu, Z., Haung, S., Fang, C., Breckon, T., & Wang, J. (2023, June). ACR: Attention Collaboration-based Regressor for Arbitrary Two-Hand Reconstruction. Presented at IEEE/CVF Conference on Computer Vision and Pattern Recognition 2023, Vancouver, BC

• Presentation Conference Type: Conference Paper (published)
• Conference Name: IEEE/CVF Conference on Computer Vision and Pattern Recognition 2023
• Start Date: Jun 17, 2023
• End Date: Jun 24, 2023
• Acceptance Date: Feb 27, 2023
• Online Publication Date: Aug 22, 2023
• Publication Date: 2023
• Deposit Date: Apr 18, 2023
• Publicly Available Date: Sep 7, 2023
• Publisher: Institute of Electrical and Electronics Engineers
• Book Title: 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
• ISBN: 9798350301304
• DOI: https://doi.org/10.1109/CVPR52729.2023.01245
• Public URL: https://durham-repository.worktribe.com/output/1134920
• Publisher URL: https://ieeexplore.ieee.org/xpl/conhome/1000147/all-proceedings
• Related Public URLs: https://breckon.org/toby/publications/papers/yu23hands.pdf