{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/synergy-between-3dmm-and-3d-landmarks-for","title":"Synergy between 3DMM and 3D Landmarks for Accurate 3D Facial Geometry","arxiv_id":"2110.09772","date":"2021-10-19","proceeding":null,"authors":["Cho-Ying Wu","Qiangeng Xu","Ulrich Neumann"],"abstract":"This work studies learning from a synergy process of 3D Morphable Models (3DMM) and 3D facial landmarks to predict complete 3D facial geometry, including 3D alignment, face orientation, and 3D face modeling. Our synergy process leverages a representation cycle for 3DMM parameters and 3D landmarks. 3D landmarks can be extracted and refined from face meshes built by 3DMM parameters. We next reverse the representation direction and show that predicting 3DMM parameters from sparse 3D landmarks improves the information flow. Together we create a synergy process that utilizes the relation between 3D landmarks and 3DMM parameters, and they collaboratively contribute to better performance. We extensively validate our contribution on full tasks of facial geometry prediction and show our superior and robust performance on these tasks for various scenarios. Particularly, we adopt only simple and widely-used network operations to attain fast and accurate facial geometry prediction. Codes and data: https://choyingw.github.io/works/SynergyNet/","url_abs":"https://arxiv.org/abs/2110.09772v3","url_pdf":"https://arxiv.org/pdf/2110.09772v3.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":"synergy-between-3dmm-and-3d-landmarks-for","repo_url":"https://github.com/choyingw/SynergyNet","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"synergy-between-3dmm-and-3d-landmarks-for","repo_url":"https://github.com/Hikaylee/SynergyNet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"mindspore","reach":null},{"paper_slug":"synergy-between-3dmm-and-3d-landmarks-for","repo_url":"https://github.com/tomas-gajarsky/facetorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"synergy-between-3dmm-and-3d-landmarks-for","repo_url":"https://gitee.com/gai-shaoyan/mind3d","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"3d-face-alignment","task_name":"3D Face Alignment"},{"task_slug":"3d-face-modeling","task_name":"3D Face Modelling"},{"task_slug":"3d-face-reconstruction","task_name":"3D Face Reconstruction"},{"task_slug":"face-alignment","task_name":"Face Alignment"},{"task_slug":"head-pose-estimation","task_name":"Head Pose Estimation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/3d-face-reconstruction-on-now-benchmark-1","task":"3D Face Reconstruction","dataset":"NoW Benchmark","model":"SynergyNet","rank_in_archive_order":13,"of":17,"metrics":{"Mean Reconstruction Error (mm)":"1.59","Median Reconstruction Error":"1.27","Stdev Reconstruction Error (mm)":"1.31"},"uses_additional_data":false},{"leaderboard":"/sota/3d-face-reconstruction-on-realy","task":"3D Face Reconstruction","dataset":"REALY","model":"SynergyNet","rank_in_archive_order":17,"of":24,"metrics":{"@cheek":"1.647 (±0.622)","@forehead":"2.679 (±0.741)","@mouth":"1.731 (±0.502)","@nose":"2.026 (±0.532)","all":"2.021"},"uses_additional_data":false},{"leaderboard":"/sota/3d-face-reconstruction-on-realy-side-view","task":"3D Face Reconstruction","dataset":"REALY (side-view)","model":"SynergyNet","rank_in_archive_order":11,"of":19,"metrics":{"@cheek":"1.662 (±0.627)","@forehead":"2.638 (±0.719)","@mouth":"1.725 (±0.533)","@nose":"2.008 (±0.526)","all":"2.008"},"uses_additional_data":false},{"leaderboard":"/sota/face-alignment-on-aflw","task":"Face Alignment","dataset":"AFLW","model":"SynergyNet","rank_in_archive_order":1,"of":3,"metrics":{"Mean NME":"4.06"},"uses_additional_data":false},{"leaderboard":"/sota/face-alignment-on-aflw2000-3d","task":"Face Alignment","dataset":"AFLW2000-3D","model":"SynergyNet-Reannotated","rank_in_archive_order":2,"of":14,"metrics":{"Balanced NME (2D Sparse Alignment)":"2.65%"},"uses_additional_data":false},{"leaderboard":"/sota/face-alignment-on-aflw2000-3d","task":"Face Alignment","dataset":"AFLW2000-3D","model":"SynergyNet","rank_in_archive_order":4,"of":14,"metrics":{"Balanced NME (2D Sparse Alignment)":"3.41%","Mean NME(3D Dense Alignment)":"4.06%"},"uses_additional_data":false},{"leaderboard":"/sota/head-pose-estimation-on-aflw2000","task":"Head Pose Estimation","dataset":"AFLW2000","model":"SynergyNet","rank_in_archive_order":4,"of":25,"metrics":{"MAE":"3.35"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2110.09772","atlas_url":"https://app.syntology.ai/?focus=2110.09772","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"2110.09772"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2110.09772\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2110.09772"},"call":"get_concepts_for_paper(arxiv_id=\"2110.09772\")"}],"by_repo":[{"repo":"choyingw/SynergyNet","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"Hikaylee/SynergyNet","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"tomas-gajarsky/facetorch","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":2,"harvested_for":["2204.00964","2205.01782"],"harvested_for_calls":[{"arxiv_id":"2204.00964","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2204.00964"},"call":"get_harvested_code_for_paper(arxiv_id=\"2204.00964\")"},{"arxiv_id":"2205.01782","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2205.01782"},"call":"get_harvested_code_for_paper(arxiv_id=\"2205.01782\")"}]},{"repo":"gitee.com/gai-shaoyan/mind3d","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0}],"by_repo_harvested_for_is":"harvested_for: the arXiv ids (as Syntology's graph holds them) of every paper whose samples Syntology's graph links to this repository, in arXiv-id order, complete; the page names the first 3 and says how many more. A link only: it does not say the papers are the same work, that one copied the other, or that the code implements this paper's method; harvested_for_calls gives the get_harvested_code_for_paper call for each arXiv-shaped id among them","by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"e59085a92f44a022a728023d75de31d629f4a79561799284a5a92a2f3788b00b","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}