ACR: Attention Collaboration-based Regressor for Arbitrary Two-Hand Reconstruction
This addresses the challenge of robust 3D hand reconstruction for computer vision applications, particularly in human-computer interaction and AR/VR, though it appears incremental in advancing existing hand reconstruction techniques.
The paper tackles the problem of reconstructing two hands from monocular RGB images in arbitrary scenarios, including occluded or separate hands, and achieves significant performance improvements over existing methods on the InterHand2.6M dataset while matching state-of-the-art single-hand methods on FreiHand.
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-of-the-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. Our code is available at https://github.com/ZhengdiYu/Arbitrary-Hands-3D-Reconstruction.