MeMaHand: Exploiting Mesh-Mano Interaction for Single Image Two-Hand Reconstruction
This work addresses the challenge of accurate two-hand reconstruction from images, which is important for applications in human-computer interaction and virtual reality, though it is incremental by combining existing parametric and non-parametric approaches.
The paper tackles the problem of reconstructing 3D meshes and estimating MANO parameters for two hands from a single RGB image, achieving promising results that outperform state-of-the-art methods on the InterHand2.6M benchmark.
Existing methods proposed for hand reconstruction tasks usually parameterize a generic 3D hand model or predict hand mesh positions directly. The parametric representations consisting of hand shapes and rotational poses are more stable, while the non-parametric methods can predict more accurate mesh positions. In this paper, we propose to reconstruct meshes and estimate MANO parameters of two hands from a single RGB image simultaneously to utilize the merits of two kinds of hand representations. To fulfill this target, we propose novel Mesh-Mano interaction blocks (MMIBs), which take mesh vertices positions and MANO parameters as two kinds of query tokens. MMIB consists of one graph residual block to aggregate local information and two transformer encoders to model long-range dependencies. The transformer encoders are equipped with different asymmetric attention masks to model the intra-hand and inter-hand attention, respectively. Moreover, we introduce the mesh alignment refinement module to further enhance the mesh-image alignment. Extensive experiments on the InterHand2.6M benchmark demonstrate promising results over the state-of-the-art hand reconstruction methods.