Interacting attention graph for single image two-hand reconstruction

M Li, L An, H Zhang, L Wu, F Chen… - Proceedings of the …, 2022 - openaccess.thecvf.com
M Li, L An, H Zhang, L Wu, F Chen, T Yu, Y Liu
Proceedings of the IEEE/CVF Conference on Computer Vision and …, 2022openaccess.thecvf.com
Graph convolutional network (GCN) has achieved great success in single hand
reconstruction task, while interacting two-hand reconstruction by GCN remains unexplored.
In this paper, we present Interacting Attention Graph Hand (IntagHand), the first graph
convolution based network that reconstructs two interacting hands from a single RGB image.
To solve occlusion and interaction challenges of two-hand reconstruction, we introduce two
novel attention based modules in each upsampling step of the original GCN. The first …
Abstract
Graph convolutional network (GCN) has achieved great success in single hand reconstruction task, while interacting two-hand reconstruction by GCN remains unexplored. In this paper, we present Interacting Attention Graph Hand (IntagHand), the first graph convolution based network that reconstructs two interacting hands from a single RGB image. To solve occlusion and interaction challenges of two-hand reconstruction, we introduce two novel attention based modules in each upsampling step of the original GCN. The first module is the pyramid image feature attention (PIFA) module, which utilizes multiresolution features to implicitly obtain vertex-to-image alignment. The second module is the cross hand attention (CHA) module that encodes the coherence of interacting hands by building dense cross-attention between two hand vertices. As a result, our model outperforms all existing two-hand reconstruction methods by a large margin on InterHand2. 6M benchmark. Moreover, ablation studies verify the effectiveness of both PIFA and CHA modules for improving the reconstruction accuracy. Results on in-the-wild images and live video streams further demonstrate the generalization ability of our network. Our code is available at https://github. com/Dw1010/IntagHand.
openaccess.thecvf.com
以上显示的是最相近的搜索结果。 查看全部搜索结果