MaskHand: Generative Masked Modeling for Robust Hand Mesh Reconstruction in the Wild

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Saleem, Muhammad Usama, Pinyoanuntapong, Ekkasit, Patel, Mayur Jagdishbhai, Xue, Hongfei, Helmy, Ahmed, Das, Srijan, Wang, Pu
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915205134417920
author Saleem, Muhammad Usama
Pinyoanuntapong, Ekkasit
Patel, Mayur Jagdishbhai
Xue, Hongfei
Helmy, Ahmed
Das, Srijan
Wang, Pu
author_facet Saleem, Muhammad Usama
Pinyoanuntapong, Ekkasit
Patel, Mayur Jagdishbhai
Xue, Hongfei
Helmy, Ahmed
Das, Srijan
Wang, Pu
contents Reconstructing a 3D hand mesh from a single RGB image is challenging due to complex articulations, self-occlusions, and depth ambiguities. Traditional discriminative methods, which learn a deterministic mapping from a 2D image to a single 3D mesh, often struggle with the inherent ambiguities in 2D-to-3D mapping. To address this challenge, we propose MaskHand, a novel generative masked model for hand mesh recovery that synthesizes plausible 3D hand meshes by learning and sampling from the probabilistic distribution of the ambiguous 2D-to-3D mapping process. MaskHand consists of two key components: (1) a VQ-MANO, which encodes 3D hand articulations as discrete pose tokens in a latent space, and (2) a Context-Guided Masked Transformer that randomly masks out pose tokens and learns their joint distribution, conditioned on corrupted token sequence, image context, and 2D pose cues. This learned distribution facilitates confidence-guided sampling during inference, producing mesh reconstructions with low uncertainty and high precision. Extensive evaluations on benchmark and real-world datasets demonstrate that MaskHand achieves state-of-the-art accuracy, robustness, and realism in 3D hand mesh reconstruction. Project website: https://m-usamasaleem.github.io/publication/MaskHand/MaskHand.html.
format Preprint
id arxiv_https___arxiv_org_abs_2412_13393
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle MaskHand: Generative Masked Modeling for Robust Hand Mesh Reconstruction in the Wild
Saleem, Muhammad Usama
Pinyoanuntapong, Ekkasit
Patel, Mayur Jagdishbhai
Xue, Hongfei
Helmy, Ahmed
Das, Srijan
Wang, Pu
Computer Vision and Pattern Recognition
Artificial Intelligence
Machine Learning
Reconstructing a 3D hand mesh from a single RGB image is challenging due to complex articulations, self-occlusions, and depth ambiguities. Traditional discriminative methods, which learn a deterministic mapping from a 2D image to a single 3D mesh, often struggle with the inherent ambiguities in 2D-to-3D mapping. To address this challenge, we propose MaskHand, a novel generative masked model for hand mesh recovery that synthesizes plausible 3D hand meshes by learning and sampling from the probabilistic distribution of the ambiguous 2D-to-3D mapping process. MaskHand consists of two key components: (1) a VQ-MANO, which encodes 3D hand articulations as discrete pose tokens in a latent space, and (2) a Context-Guided Masked Transformer that randomly masks out pose tokens and learns their joint distribution, conditioned on corrupted token sequence, image context, and 2D pose cues. This learned distribution facilitates confidence-guided sampling during inference, producing mesh reconstructions with low uncertainty and high precision. Extensive evaluations on benchmark and real-world datasets demonstrate that MaskHand achieves state-of-the-art accuracy, robustness, and realism in 3D hand mesh reconstruction. Project website: https://m-usamasaleem.github.io/publication/MaskHand/MaskHand.html.
title MaskHand: Generative Masked Modeling for Robust Hand Mesh Reconstruction in the Wild
topic Computer Vision and Pattern Recognition
Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2412.13393