3D Hand Reconstruction via Aggregating Intra and Inter Graphs Guided by Prior Knowledge for Hand-Object Interaction Scenario
This addresses the problem of severe hand occlusion in human-computer interaction for applications like VR/AR, representing an incremental improvement over prior work.
The paper tackles 3D hand reconstruction in hand-object interaction scenarios by proposing a network that combines model-based and model-free approaches to balance accuracy and physical plausibility, achieving competitive performance on benchmark datasets HO3DV2 and Dex-YCB and outperforming existing methods.
Recently, 3D hand reconstruction has gained more attention in human-computer cooperation, especially for hand-object interaction scenario. However, it still remains huge challenge due to severe hand-occlusion caused by interaction, which contain the balance of accuracy and physical plausibility, highly nonlinear mapping of model parameters and occlusion feature enhancement. To overcome these issues, we propose a 3D hand reconstruction network combining the benefits of model-based and model-free approaches to balance accuracy and physical plausibility for hand-object interaction scenario. Firstly, we present a novel MANO pose parameters regression module from 2D joints directly, which avoids the process of highly nonlinear mapping from abstract image feature and no longer depends on accurate 3D joints. Moreover, we further propose a vertex-joint mutual graph-attention model guided by MANO to jointly refine hand meshes and joints, which model the dependencies of vertex-vertex and joint-joint and capture the correlation of vertex-joint for aggregating intra-graph and inter-graph node features respectively. The experimental results demonstrate that our method achieves a competitive performance on recently benchmark datasets HO3DV2 and Dex-YCB, and outperforms all only model-base approaches and model-free approaches.