{"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/learning-an-animatable-detailed-3d-face-model","title":"Learning an Animatable Detailed 3D Face Model from In-The-Wild Images","arxiv_id":"2012.04012","date":"2020-12-07","proceeding":null,"authors":["Yao Feng","Haiwen Feng","Michael J. Black","Timo Bolkart"],"abstract":"While current monocular 3D face reconstruction methods can recover fine geometric details, they suffer several limitations. Some methods produce faces that cannot be realistically animated because they do not model how wrinkles vary with expression. Other methods are trained on high-quality face scans and do not generalize well to in-the-wild images. We present the first approach that regresses 3D face shape and animatable details that are specific to an individual but change with expression. Our model, DECA (Detailed Expression Capture and Animation), is trained to robustly produce a UV displacement map from a low-dimensional latent representation that consists of person-specific detail parameters and generic expression parameters, while a regressor is trained to predict detail, shape, albedo, expression, pose and illumination parameters from a single image. To enable this, we introduce a novel detail-consistency loss that disentangles person-specific details from expression-dependent wrinkles. This disentanglement allows us to synthesize realistic person-specific wrinkles by controlling expression parameters while keeping person-specific details unchanged. DECA is learned from in-the-wild images with no paired 3D supervision and achieves state-of-the-art shape reconstruction accuracy on two benchmarks. Qualitative results on in-the-wild data demonstrate DECA's robustness and its ability to disentangle identity- and expression-dependent details enabling animation of reconstructed faces. The model and code are publicly available at https://deca.is.tue.mpg.de.","url_abs":"https://arxiv.org/abs/2012.04012v2","url_pdf":"https://arxiv.org/pdf/2012.04012v2.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":"learning-an-animatable-detailed-3d-face-model","repo_url":"https://github.com/YadiraF/DECA","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"learning-an-animatable-detailed-3d-face-model","repo_url":"https://github.com/yfeng95/deca","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"3d-face-alignment","task_name":"3D Face Alignment"},{"task_slug":"3d-face-animation","task_name":"3D Face Animation"},{"task_slug":"3d-face-modeling","task_name":"3D Face Modelling"},{"task_slug":"3d-face-reconstruction","task_name":"3D Face Reconstruction"},{"task_slug":"disentanglement","task_name":"Disentanglement"},{"task_slug":"face-alignment","task_name":"Face Alignment"},{"task_slug":"face-model","task_name":"Face Model"},{"task_slug":"face-reconstruction","task_name":"Face Reconstruction"}],"methods":[{"method_slug":null,"method_name":"DECA"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/3d-face-reconstruction-on-now-benchmark-1","task":"3D Face Reconstruction","dataset":"NoW Benchmark","model":"DECA","rank_in_archive_order":5,"of":17,"metrics":{"Mean Reconstruction Error (mm)":"1.38","Median Reconstruction Error":"1.09","Stdev Reconstruction Error (mm)":"1.18"},"uses_additional_data":false},{"leaderboard":"/sota/3d-face-reconstruction-on-realy","task":"3D Face Reconstruction","dataset":"REALY","model":"DECA-c","rank_in_archive_order":14,"of":24,"metrics":{"@cheek":"1.479 (±0.535)","@forehead":"2.394 (±0.576)","@mouth":"2.516 (±0.839)","@nose":"1.697 (±0.355)","all":"2.010"},"uses_additional_data":false},{"leaderboard":"/sota/3d-face-reconstruction-on-realy","task":"3D Face Reconstruction","dataset":"REALY","model":"DECA-f","rank_in_archive_order":20,"of":24,"metrics":{"@cheek":"1.443 (±0.498)","@forehead":"2.457 (±0.559)","@mouth":"2.802 (±0.868)","@nose":"2.138 (±0.461)","all":"2.210"},"uses_additional_data":false},{"leaderboard":"/sota/3d-face-reconstruction-on-realy-side-view","task":"3D Face Reconstruction","dataset":"REALY (side-view)","model":"DECA-c","rank_in_archive_order":13,"of":19,"metrics":{"@cheek":"1.630 (±1.135)","@forehead":"2.423 (±0.720)","@mouth":"2.472 (±1.079)","@nose":"1.903 (±1.050)","all":"2.107"},"uses_additional_data":false},{"leaderboard":"/sota/3d-face-reconstruction-on-realy-side-view","task":"3D Face Reconstruction","dataset":"REALY (side-view)","model":"DECA-f","rank_in_archive_order":17,"of":19,"metrics":{"@cheek":"1.555 (±0.822)","@forehead":"2.519 (±0.718)","@mouth":"2.684 (±1.041)","@nose":"2.286 (±1.103)","all":"2.261"},"uses_additional_data":false},{"leaderboard":"/sota/3d-face-reconstruction-on-stirling-hq-fg2018","task":"3D Face Reconstruction","dataset":"Stirling-HQ (FG2018 3D face reconstruction challenge)","model":"DECA","rank_in_archive_order":1,"of":4,"metrics":{"Mean Reconstruction Error (mm)":"1.89"},"uses_additional_data":false},{"leaderboard":"/sota/3d-face-reconstruction-on-stirling-lq-fg2018","task":"3D Face Reconstruction","dataset":"Stirling-LQ (FG2018 3D face reconstruction challenge)","model":"DECA","rank_in_archive_order":1,"of":4,"metrics":{"Mean Reconstruction Error (mm)":"1.91"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2012.04012","atlas_url":"https://app.syntology.ai/?focus=2012.04012","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":"2012.04012"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2012.04012\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2012.04012"},"call":"get_concepts_for_paper(arxiv_id=\"2012.04012\")"}],"by_repo":[{"repo":"YadiraF/DECA","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"yfeng95/deca","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0}],"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":"bc07c825b94ab25489af10496de734569712fb0eba8ebf2cb6075a37aa1d2625","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}