{"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/dad-3dheads-a-large-scale-dense-accurate-and","title":"DAD-3DHeads: A Large-scale Dense, Accurate and Diverse Dataset for 3D Head Alignment from a Single Image","arxiv_id":"2204.03688","date":"2022-04-07","proceeding":"CVPR 2022 1","authors":["Tetiana Martyniuk","Orest Kupyn","Yana Kurlyak","Igor Krashenyi","Jiři Matas","Viktoriia Sharmanska"],"abstract":"We present DAD-3DHeads, a dense and diverse large-scale dataset, and a robust model for 3D Dense Head Alignment in the wild. It contains annotations of over 3.5K landmarks that accurately represent 3D head shape compared to the ground-truth scans. The data-driven model, DAD-3DNet, trained on our dataset, learns shape, expression, and pose parameters, and performs 3D reconstruction of a FLAME mesh. The model also incorporates a landmark prediction branch to take advantage of rich supervision and co-training of multiple related tasks. Experimentally, DAD-3DNet outperforms or is comparable to the state-of-the-art models in (i) 3D Head Pose Estimation on AFLW2000-3D and BIWI, (ii) 3D Face Shape Reconstruction on NoW and Feng, and (iii) 3D Dense Head Alignment and 3D Landmarks Estimation on DAD-3DHeads dataset. Finally, the diversity of DAD-3DHeads in camera angles, facial expressions, and occlusions enables a benchmark to study in-the-wild generalization and robustness to distribution shifts. The dataset webpage is https://p.farm/research/dad-3dheads.","url_abs":"https://arxiv.org/abs/2204.03688v2","url_pdf":"https://arxiv.org/pdf/2204.03688v2.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":"dad-3dheads-a-large-scale-dense-accurate-and","repo_url":"https://github.com/PinataFarms/DAD-3DHeads","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}}],"tasks":[{"task_slug":"3d-reconstruction","task_name":"3D Reconstruction"},{"task_slug":"diversity","task_name":"Diversity"},{"task_slug":"head-pose-estimation","task_name":"Head Pose Estimation"},{"task_slug":"pose-estimation","task_name":"Pose Estimation"}],"methods":[],"datasets_introduced":[{"slug":"dad-3dheads","name":"DAD-3DHeads","full_name":"DAD-3DHeads dataset"}],"methods_introduced":[],"results":[{"leaderboard":"/sota/head-pose-estimation-on-aflw2000","task":"Head Pose Estimation","dataset":"AFLW2000","model":"DAD-3DNet","rank_in_archive_order":7,"of":25,"metrics":{"MAE":"3.66"},"uses_additional_data":false},{"leaderboard":"/sota/head-pose-estimation-on-biwi","task":"Head Pose Estimation","dataset":"BIWI","model":"DAD-3DNet","rank_in_archive_order":26,"of":29,"metrics":{"MAE (trained with BIWI data)":"3.98"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2204.03688","atlas_url":"https://app.syntology.ai/?focus=2204.03688","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}