|国家预印本平台
首页|M3DHMR: Monocular 3D Hand Mesh Recovery

M3DHMR: Monocular 3D Hand Mesh Recovery

M3DHMR: Monocular 3D Hand Mesh Recovery

来源:Arxiv_logoArxiv
英文摘要

Monocular 3D hand mesh recovery is challenging due to high degrees of freedom of hands, 2D-to-3D ambiguity and self-occlusion. Most existing methods are either inefficient or less straightforward for predicting the position of 3D mesh vertices. Thus, we propose a new pipeline called Monocular 3D Hand Mesh Recovery (M3DHMR) to directly estimate the positions of hand mesh vertices. M3DHMR provides 2D cues for 3D tasks from a single image and uses a new spiral decoder consist of several Dynamic Spiral Convolution (DSC) Layers and a Region of Interest (ROI) Layer. On the one hand, DSC Layers adaptively adjust the weights based on the vertex positions and extract the vertex features in both spatial and channel dimensions. On the other hand, ROI Layer utilizes the physical information and refines mesh vertices in each predefined hand region separately. Extensive experiments on popular dataset FreiHAND demonstrate that M3DHMR significantly outperforms state-of-the-art real-time methods.

Yihong Lin、Xianjia Wu、Xilai Wang、Jianqiao Hu、Songju Lei、Xiandong Li、Wenxiong Kang

计算技术、计算机技术

Yihong Lin,Xianjia Wu,Xilai Wang,Jianqiao Hu,Songju Lei,Xiandong Li,Wenxiong Kang.M3DHMR: Monocular 3D Hand Mesh Recovery[EB/OL].(2025-05-26)[2025-06-24].https://arxiv.org/abs/2505.20058.点此复制

评论