paper-with-me

홈 › Papers

M3DHMR: Monocular 3D Hand Mesh Recovery

2025-05-26 · Yihong Lin, Xianjia Wu, Xilai Wang, Jianqiao Hu, Songju Lei, Xiandong Li, Wenxiong Kang

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.

📄 PDF Abstract BibTeX arXiv:2505.20058

Code (0)

등록된 구현이 없습니다.

Tasks

Decoder

Methods 이 논문이 사용한 방법론

Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…

Similar Papers 제목 키워드 기반

ADHMR: Aligning Diffusion-based Human Mesh Recovery via Direct Preference Optimization

2025-05-15 · Wenhao Shen, Wanqi Yin, Xiaofeng Yang, Cheng Chen 외

Human mesh recovery (HMR) from a single image is inherently ill-posed due to depth ambiguity and occlusions. Probabilistic methods have tried to solve this by generating numerous plausible 3D human mesh predictions, but …

Human Mesh Recovery

FactorizedHMR: A Hybrid Framework for Video Human Mesh Recovery

2026-05-14 · Patrick Kwon, Chen Chen arxiv

Human Mesh Recovery (HMR) is fundamentally ambiguous: under occlusion or weak depth cues, multiple 3D bodies can explain the same image evidence. This ambiguity is not uniform across the body, as torso pose and root stru…

Human Mesh Recovery

End-to-end Hand Mesh Recovery from a Monocular RGB Image

2019-02-25 · ICCV 2019 10 · Xiong Zhang, Qiang Li, Hong Mo, Wenbo Zhang 외

In this paper, we present a HAnd Mesh Recovery (HAMR) framework to tackle the problem of reconstructing the full 3D mesh of a human hand from a single RGB image. In contrast to existing research on 2D or 3D hand pose est…

3D Hand Pose EstimationHand Pose EstimationPose Estimation

DanceHMR: Hand-Aware Whole-Body Human Mesh Recovery from Monocular Videos

2026-05-18 · Wenhao Shen, Ming Zhou, Hengyuan Zhang, Siyuan Bian 외 arxiv

Monocular video human mesh recovery is essential for digital humans, avatar animation, and embodied simulation, where both temporal stability and expressive whole-body motion are required. Existing video HMR methods prod…

Human Mesh Recovery

HandTailor: Towards High-Precision Monocular 3D Hand Recovery

2021-02-18 · Jun Lv, Wenqiang Xu, Lixin Yang, Sucheng Qian 외

3D hand pose estimation and shape recovery are challenging tasks in computer vision. We introduce a novel framework HandTailor, which combines a learning-based hand module and an optimization-based tailor module to achie…

3D Hand Pose EstimationCPUHand Pose EstimationPose Estimation+1