{"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/two-stage-convolutional-part-heatmap","title":"Two-stage Convolutional Part Heatmap Regression for the 1st 3D Face Alignment in the Wild (3DFAW) Challenge","arxiv_id":"1609.09545","date":"2016-09-29","proceeding":null,"authors":["Adrian Bulat","Georgios Tzimiropoulos"],"abstract":"This paper describes our submission to the 1st 3D Face Alignment in the Wild\n(3DFAW) Challenge. Our method builds upon the idea of convolutional part\nheatmap regression [1], extending it for 3D face alignment. Our method\ndecomposes the problem into two parts: (a) X,Y (2D) estimation and (b) Z\n(depth) estimation. At the first stage, our method estimates the X,Y\ncoordinates of the facial landmarks by producing a set of 2D heatmaps, one for\neach landmark, using convolutional part heatmap regression. Then, these\nheatmaps, alongside the input RGB image, are used as input to a very deep\nsubnetwork trained via residual learning for regressing the Z coordinate. Our\nmethod ranked 1st in the 3DFAW Challenge, surpassing the second best result by\nmore than 22%.","url_abs":"http://arxiv.org/abs/1609.09545v1","url_pdf":"http://arxiv.org/pdf/1609.09545v1.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":"two-stage-convolutional-part-heatmap","repo_url":"https://github.com/1adrianb/face-alignment","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"BSD-3-Clause"}}],"tasks":[{"task_slug":"3d-face-alignment","task_name":"3D Face Alignment"},{"task_slug":"depth-estimation","task_name":"Depth Estimation"},{"task_slug":"face-alignment","task_name":"Face Alignment"},{"task_slug":"regression-1","task_name":"regression"}],"methods":[{"method_slug":"heatmap","method_name":"Heatmap"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/face-alignment-on-3dfaw-1","task":"Face Alignment","dataset":"3DFAW","model":"3D Face alignment","rank_in_archive_order":1,"of":1,"metrics":{"CVGTCE":"3.4767%","GTE":"4.5623"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/1609.09545","atlas_url":"https://app.syntology.ai/?focus=1609.09545","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}