{"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/mesh-graphormer","title":"Mesh Graphormer","arxiv_id":"2104.00272","date":"2021-04-01","proceeding":"ICCV 2021 10","authors":["Kevin Lin","Lijuan Wang","Zicheng Liu"],"abstract":"We present a graph-convolution-reinforced transformer, named Mesh Graphormer, for 3D human pose and mesh reconstruction from a single image. Recently both transformers and graph convolutional neural networks (GCNNs) have shown promising progress in human mesh reconstruction. Transformer-based approaches are effective in modeling non-local interactions among 3D mesh vertices and body joints, whereas GCNNs are good at exploiting neighborhood vertex interactions based on a pre-specified mesh topology. In this paper, we study how to combine graph convolutions and self-attentions in a transformer to model both local and global interactions. Experimental results show that our proposed method, Mesh Graphormer, significantly outperforms the previous state-of-the-art methods on multiple benchmarks, including Human3.6M, 3DPW, and FreiHAND datasets. Code and pre-trained models are available at https://github.com/microsoft/MeshGraphormer","url_abs":"https://arxiv.org/abs/2104.00272v2","url_pdf":"https://arxiv.org/pdf/2104.00272v2.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":[{"paper_slug":"mesh-graphormer","repo_url":"https://github.com/microsoft/meshgraphormer","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"mesh-graphormer","repo_url":"https://github.com/2024-MindSpore-1/Code2/tree/main/model-1/graphormer","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"mesh-graphormer","repo_url":"https://github.com/MS-P3/code5/tree/main/graphormer","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null}],"tasks":[{"task_slug":"3d-hand-pose-estimation","task_name":"3D Hand Pose Estimation"},{"task_slug":"3d-human-pose-estimation","task_name":"3D Human Pose Estimation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/3d-hand-pose-estimation-on-freihand","task":"3D Hand Pose Estimation","dataset":"FreiHAND","model":"MeshGraphormer","rank_in_archive_order":9,"of":33,"metrics":{"PA-F@15mm":"0.986","PA-F@5mm":"0.764","PA-MPJPE":"5.9","PA-MPVPE":"6.0"},"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":"MeshGraphormer","rank_in_archive_order":6,"of":10,"metrics":{"PCK@0.05 (Ego4D) All":"14.6","PCK@0.05 (Ego4D) Occ":"8.3","PCK@0.05 (Ego4D) Visible":"18.4","PCK@0.05 (New Days) All":"16.8","PCK@0.05 (NewDays) Occ":"7.9","PCK@0.05 (NewDays) Visible":"22.3","PCK@0.05 (VISOR) All":"19.1","PCK@0.05 (VISOR) Occ":"10.9","PCK@0.05 (VISOR) Visible":"23.6"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2104.00272","atlas_url":"https://app.syntology.ai/?focus=2104.00272","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}