Towards Accurate Alignment in Real-time 3D Hand-Mesh Reconstruction

Xiao Tang, Tianyu Wang, and Chi-Wing Fu Presented in ICCV 2021

Towards finger-level alignment between the predicted 3D hand mesh and the real hand in the input image for AR applications.


Abstrast

3D hand-mesh reconstruction from RGB images facilitates many applications, including augmented reality (AR). However, this requires not only real-time speed and accurate hand pose and shape but also plausible mesh-image alignment. While existing works already achieve promising results, meeting all three requirements is very challenging. This paper presents a novel pipeline by decoupling the hand-mesh reconstruction task into three stages: a joint stage to predict hand joints and segmentation; a mesh stage to predict a rough hand mesh; and a refine stage to fine-tune it with an offset mesh for mesh-image alignment. With careful design in the network structure and in the loss functions, we can promote high-quality finger-level mesh-image alignment and drive the models together to deliver real-time predictions. Extensive quantitative and qualitative results on benchmark datasets demonstrate that the quality of our results outperforms the state-of-the-art methods on hand-mesh/pose precision and hand-image alignment. In the end, we also showcase several real-time AR scenarios.


Video

To release after the ICCV conference


Comparison on FreiHAND


More Results


Links

Paper:
Code: