{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/mmhmr-generative-masked-modeling-for-hand","title":"MMHMR: Generative Masked Modeling for Hand Mesh Recovery","arxiv_id":"2412.13393","date":"2024-12-18","proceeding":null,"authors":["Muhammad Usama Saleem","Ekkasit Pinyoanuntapong","Mayur Jagdishbhai Patel","Hongfei Xue","Ahmed Helmy","Srijan Das","Pu Wang"],"abstract":"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 MMHMR, 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. MMHMR 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 sequences, 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 MMHMR achieves state-of-the-art accuracy, robustness, and realism in 3D hand mesh reconstruction. Project website: https://m-usamasaleem.github.io/publication/MMHMR/mmhmr.html","url_abs":"https://arxiv.org/abs/2412.13393v1","url_pdf":"https://arxiv.org/pdf/2412.13393v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[],"tasks":[{"task_slug":"3d-hand-pose-estimation","task_name":"3D Hand Pose Estimation"}],"methods":[{"method_slug":"absolute-position-encodings","method_name":"Absolute Position Encodings"},{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"label-smoothing","method_name":"Label Smoothing"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"position-wise-feed-forward-layer","method_name":"Position-Wise Feed-Forward Layer"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"transformer","method_name":"Transformer"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/3d-hand-pose-estimation-on-dexycb","task":"3D Hand Pose Estimation","dataset":"DexYCB","model":"MaskHand","rank_in_archive_order":2,"of":11,"metrics":{"Average MPJPE (mm)":"11.7","MPVPE":"11.2","PA-MPVPE":"4.9","Procrustes-Aligned MPJPE":"5.0"},"uses_additional_data":false},{"leaderboard":"/sota/3d-hand-pose-estimation-on-freihand","task":"3D Hand Pose Estimation","dataset":"FreiHAND","model":"MaskHand","rank_in_archive_order":4,"of":33,"metrics":{"PA-F@15mm":"0.991","PA-F@5mm":"0.801","PA-MPJPE":"5.5","PA-MPVPE":"5.4"},"uses_additional_data":false},{"leaderboard":"/sota/3d-hand-pose-estimation-on-hint-hand","task":"3D Hand Pose Estimation","dataset":"HInt: Hand Interactions in the wild","model":"MaskHand","rank_in_archive_order":4,"of":10,"metrics":{"PCK@0.05 (Ego4D) All":"46.4","PCK@0.05 (Ego4D) Occ":"29.4","PCK@0.05 (Ego4D) Visible":"59.3","PCK@0.05 (New Days) All":"48.7","PCK@0.05 (NewDays) Occ":"29.4","PCK@0.05 (NewDays) Visible":"61.0","PCK@0.05 (VISOR) All":"46.1","PCK@0.05 (VISOR) Occ":"31.4","PCK@0.05 (VISOR) Visible":"62.1"},"uses_additional_data":false},{"leaderboard":"/sota/3d-hand-pose-estimation-on-ho-3d-v3","task":"3D Hand Pose Estimation","dataset":"HO-3D v3","model":"MaskHand","rank_in_archive_order":2,"of":8,"metrics":{"AUC_J":"0.860","AUC_V":"0.860","F@15mm":"0.984","F@5mm":"0.663","PA-MPJPE":"7.0","PA-MPVPE":"7.0"},"uses_additional_data":false}],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}