{"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/3d-face-reconstruction-with-dense-landmarks","title":"3D face reconstruction with dense landmarks","arxiv_id":"2204.02776","date":"2022-04-06","proceeding":null,"authors":["Erroll Wood","Tadas Baltrusaitis","Charlie Hewitt","Matthew Johnson","Jingjing Shen","Nikola Milosavljevic","Daniel Wilde","Stephan Garbin","Chirag Raman","Jamie Shotton","Toby Sharp","Ivan Stojiljkovic","Tom Cashman","Julien Valentin"],"abstract":"Landmarks often play a key role in face analysis, but many aspects of identity or expression cannot be represented by sparse landmarks alone. Thus, in order to reconstruct faces more accurately, landmarks are often combined with additional signals like depth images or techniques like differentiable rendering. Can we keep things simple by just using more landmarks? In answer, we present the first method that accurately predicts 10x as many landmarks as usual, covering the whole head, including the eyes and teeth. This is accomplished using synthetic training data, which guarantees perfect landmark annotations. By fitting a morphable model to these dense landmarks, we achieve state-of-the-art results for monocular 3D face reconstruction in the wild. We show that dense landmarks are an ideal signal for integrating face shape information across frames by demonstrating accurate and expressive facial performance capture in both monocular and multi-view scenarios. This approach is also highly efficient: we can predict dense landmarks and fit our 3D face model at over 150FPS on a single CPU thread. Please see our website: https://microsoft.github.io/DenseLandmarks/.","url_abs":"https://arxiv.org/abs/2204.02776v2","url_pdf":"https://arxiv.org/pdf/2204.02776v2.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-face-reconstruction","task_name":"3D Face Reconstruction"},{"task_slug":null,"task_name":"CPU"},{"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":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/3d-face-reconstruction-on-florence","task":"3D Face Reconstruction","dataset":"Florence","model":"DenseLandmarks (Multi-view)","rank_in_archive_order":9,"of":16,"metrics":{"RMSE Cooperative":"1.43","RMSE Indoor":"1.42","RMSE Outdoor":"1.42"},"uses_additional_data":false},{"leaderboard":"/sota/3d-face-reconstruction-on-florence","task":"3D Face Reconstruction","dataset":"Florence","model":"DenseLandmarks (Single-view)","rank_in_archive_order":11,"of":16,"metrics":{"RMSE Cooperative":"1.64","RMSE Indoor":"1.62","RMSE Outdoor":"1.61"},"uses_additional_data":false},{"leaderboard":"/sota/3d-face-reconstruction-on-now-benchmark-1","task":"3D Face Reconstruction","dataset":"NoW Benchmark","model":"DenseLandmarks (Multi-view)","rank_in_archive_order":1,"of":17,"metrics":{"Mean Reconstruction Error (mm)":"1.01","Median Reconstruction Error":"0.81","Stdev Reconstruction Error (mm)":"0.84"},"uses_additional_data":false},{"leaderboard":"/sota/3d-face-reconstruction-on-now-benchmark-1","task":"3D Face Reconstruction","dataset":"NoW Benchmark","model":"DenseLandmarks (Single-view)","rank_in_archive_order":3,"of":17,"metrics":{"Mean Reconstruction Error (mm)":"1.28","Median Reconstruction Error":"1.02","Stdev Reconstruction Error (mm)":"1.08"},"uses_additional_data":false},{"leaderboard":"/sota/face-alignment-on-300w","task":"Face Alignment","dataset":"300W","model":"DenseLandmarks (GNLL)","rank_in_archive_order":44,"of":48,"metrics":{"NME_inter-ocular (%, Challenge)":"4.8","NME_inter-ocular (%, Common)":"3.03"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2204.02776","atlas_url":"https://app.syntology.ai/?focus=2204.02776","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":"2204.02776"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2204.02776\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2204.02776"},"call":"get_concepts_for_paper(arxiv_id=\"2204.02776\")"}],"by_repo":[],"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":"the archive holds no code link for this paper","arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"466fa8374440e48da30ff729bcbe286680168f4f3721474cb22898d301f3917a","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}