Interacting Attention Graph for Single Image Two-Hand Reconstruction

03/17/2022
by   Mengcheng Li, et al.
9

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.

READ FULL TEXT

page 1

page 4

page 5

page 7

page 8

research
08/21/2022

LWA-HAND: Lightweight Attention Hand for Interacting Hand Reconstruction

Hand reconstruction has achieved great success in real-time applications...
research
03/10/2023

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

Reconstructing two hands from monocular RGB images is challenging due to...
research
02/28/2023

Im2Hands: Learning Attentive Implicit Representation of Interacting Two-Hand Shapes

We present Implicit Two Hands (Im2Hands), the first neural implicit repr...
research
02/05/2023

See You Soon: Decoupled Iterative Refinement Framework for Interacting Hands Reconstruction from a Single RGB Image

Reconstructing interacting hands from a single RGB image is a very chall...
research
03/23/2023

Bringing Inputs to Shared Domains for 3D Interacting Hands Recovery in the Wild

Despite recent achievements, existing 3D interacting hands recovery meth...
research
07/18/2023

Pixel-wise Graph Attention Networks for Person Re-identification

Graph convolutional networks (GCN) is widely used to handle irregular da...
research
04/09/2019

Contextual Attention for Hand Detection in the Wild

We present Hand-CNN, a novel convolutional network architecture for dete...

Please sign up or login with your details

Forgot password? Click here to reset