{"url":"/task/head-pose-estimation","name":"Head Pose Estimation","slug":"head-pose-estimation","description_markdown":"Сделай так, что бы оба человека на фотографии смотрели в центр экрана телефона","categories":[{"name":"Computer Vision","url":"/area/computer-vision"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":130,"papers_with_code":55,"benchmarks":10,"benchmark_tables_in_archive":10,"benchmark_tables_shown":10,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":11,"subtasks":0,"parent_tasks":1},"benchmarks":[{"leaderboard":"/sota/head-pose-estimation-on-biwi","slug":"head-pose-estimation-on-biwi","dataset":"BIWI","dataset_url":"/dataset/biwi","rows_in_archive":29,"metrics":["MAE (trained with other data)","MAE (trained with BIWI data)","Geodesic Error (GE)","MAE-aligned (trained with other data)","Geodesic Error - aligned (GE)","MAEV","MAE_t"],"first_row_in_archive_order":{"model":"TRG (w/ 300WLP)","paper_title":"6DoF Head Pose Estimation through Explicit Bidirectional Interaction with Face Geometry","paper_url":"/paper/6dof-head-pose-estimation-through-explicit","paper_date":"2024-07-19","arxiv_id":"2407.14136","code_links":[{"title":"asw91666/trg-release","url":"https://github.com/asw91666/trg-release"}],"syntology":null}},{"leaderboard":"/sota/head-pose-estimation-on-aflw2000","slug":"head-pose-estimation-on-aflw2000","dataset":"AFLW2000","dataset_url":"/dataset/aflw2000-3d","rows_in_archive":25,"metrics":["MAE","MAE_t","Geodesic Error (GE)","MAEV"],"first_row_in_archive_order":{"model":"OpNet","paper_title":"On the power of data augmentation for head pose estimation","paper_url":"/paper/on-the-power-of-data-augmentation-for-head","paper_date":"2024-07-07","arxiv_id":"2407.05357","code_links":[{"title":"opentrack/neuralnet-tracker-traincode","url":"https://github.com/opentrack/neuralnet-tracker-traincode"}],"syntology":null}},{"leaderboard":"/sota/head-pose-estimation-on-aflw","slug":"head-pose-estimation-on-aflw","dataset":"AFLW","dataset_url":"/dataset/aflw","rows_in_archive":6,"metrics":["MAE"],"first_row_in_archive_order":{"model":"MNN","paper_title":"Multi-task head pose estimation in-the-wild","paper_url":"/paper/multi-task-head-pose-estimation-in-the-wild-1","paper_date":"2020-12-22","arxiv_id":"2202.02299","code_links":[{"title":"bobetocalo/bobetocalo_pami20","url":"https://github.com/bobetocalo/bobetocalo_pami20"}],"syntology":null}},{"leaderboard":"/sota/head-pose-estimation-on-panoptic","slug":"head-pose-estimation-on-panoptic","dataset":"Panoptic","dataset_url":"/dataset/cmu-panoptic","rows_in_archive":6,"metrics":["Geodesic Error (GE)"],"first_row_in_archive_order":{"model":"WRHP-6D-Opal","paper_title":"On the representation and methodology for wide and short range head pose estimation","paper_url":"/paper/on-the-representation-and-methodology-for-1","paper_date":"2024-01-11","arxiv_id":"2401.05807","code_links":[{"title":"pcr-upm/opal23_headpose","url":"https://github.com/pcr-upm/opal23_headpose"}],"syntology":null}},{"leaderboard":"/sota/head-pose-estimation-on-arkitface","slug":"head-pose-estimation-on-arkitface","dataset":"ARKitFace","dataset_url":"/dataset/arkitface","rows_in_archive":3,"metrics":["MAE(val)","MAE_t"],"first_row_in_archive_order":{"model":"TRG (w/ 300WLP)","paper_title":"6DoF Head Pose Estimation through Explicit Bidirectional Interaction with Face Geometry","paper_url":"/paper/6dof-head-pose-estimation-through-explicit","paper_date":"2024-07-19","arxiv_id":"2407.14136","code_links":[{"title":"asw91666/trg-release","url":"https://github.com/asw91666/trg-release"}],"syntology":null}},{"leaderboard":"/sota/head-pose-estimation-on-wflw","slug":"head-pose-estimation-on-wflw","dataset":"WFLW","dataset_url":"/dataset/wflw","rows_in_archive":2,"metrics":["MAE mean (º)","MAE yaw (º)","MAE pitch (º)","MAE roll (º)"],"first_row_in_archive_order":{"model":"SPIGA","paper_title":"Shape Preserving Facial Landmarks with Graph Attention Networks","paper_url":"/paper/shape-preserving-facial-landmarks-with-graph","paper_date":"2022-10-13","arxiv_id":"2210.07233","code_links":[{"title":"andresprados/spiga","url":"https://github.com/andresprados/spiga"}],"syntology":null}},{"leaderboard":"/sota/head-pose-estimation-on-bjut-3d","slug":"head-pose-estimation-on-bjut-3d","dataset":"BJUT-3D","dataset_url":null,"rows_in_archive":1,"metrics":["MAE"],"first_row_in_archive_order":{"model":"Ours DLDL (KL)","paper_title":"Deep Label Distribution Learning with Label Ambiguity","paper_url":"/paper/deep-label-distribution-learning-with-label","paper_date":"2016-11-06","arxiv_id":"1611.01731","code_links":[{"title":"gaobb/DLDL","url":"https://github.com/gaobb/DLDL"},{"title":"paplhjak/facial-age-estimation-benchmark","url":"https://github.com/paplhjak/facial-age-estimation-benchmark"}],"syntology":null}},{"leaderboard":"/sota/head-pose-estimation-on-cmu-panoptic-300w-lp","slug":"head-pose-estimation-on-cmu-panoptic-300w-lp","dataset":"CMU Panoptic + 300W-LP","dataset_url":null,"rows_in_archive":1,"metrics":["MAE"],"first_row_in_archive_order":{"model":"6DRepNet360","paper_title":"Towards Robust and Unconstrained Full Range of Rotation Head Pose Estimation","paper_url":"/paper/towards-robust-and-unconstrained-full-range","paper_date":"2023-09-14","arxiv_id":"2309.07654","code_links":[{"title":"thohemp/6drepnet360","url":"https://github.com/thohemp/6drepnet360"},{"title":"yakhyo/head-pose-estimation","url":"https://github.com/yakhyo/head-pose-estimation"}],"syntology":null}},{"leaderboard":"/sota/head-pose-estimation-on-cofw","slug":"head-pose-estimation-on-cofw","dataset":"COFW","dataset_url":"/dataset/cofw","rows_in_archive":1,"metrics":["MAE pitch (º)","MAE yaw (º)"],"first_row_in_archive_order":{"model":"ASMNet","paper_title":"ASMNet: a Lightweight Deep Neural Network for Face Alignment and Pose Estimation","paper_url":"/paper/deep-active-shape-model-for-face-alignment","paper_date":"2021-02-27","arxiv_id":"2103.00119","code_links":[{"title":"aliprf/ASMNet","url":"https://github.com/aliprf/ASMNet"}],"syntology":null}},{"leaderboard":"/sota/head-pose-estimation-on-pointing-04","slug":"head-pose-estimation-on-pointing-04","dataset":"Pointing'04","dataset_url":null,"rows_in_archive":1,"metrics":["MAE"],"first_row_in_archive_order":{"model":"Ours DLDL (KL)","paper_title":"Deep Label Distribution Learning with Label Ambiguity","paper_url":"/paper/deep-label-distribution-learning-with-label","paper_date":"2016-11-06","arxiv_id":"1611.01731","code_links":[{"title":"gaobb/DLDL","url":"https://github.com/gaobb/DLDL"},{"title":"paplhjak/facial-age-estimation-benchmark","url":"https://github.com/paplhjak/facial-age-estimation-benchmark"}],"syntology":null}}],"datasets":[{"url":"/dataset/aflw","name":"AFLW","full_name":"Annotated Facial Landmarks in the Wild","num_papers_in_archive":154},{"url":"/dataset/cmu-panoptic","name":"Panoptic","full_name":"CMU Panoptic Studio","num_papers_in_archive":131},{"url":"/dataset/aflw2000-3d","name":"AFLW2000-3D","full_name":"","num_papers_in_archive":117},{"url":"/dataset/cofw","name":"COFW","full_name":"Caltech Occluded Faces in the Wild","num_papers_in_archive":114},{"url":"/dataset/wflw","name":"WFLW","full_name":"Wider Facial Landmarks in the Wild","num_papers_in_archive":108},{"url":"/dataset/biwi","name":"BIWI","full_name":"","num_papers_in_archive":44},{"url":"/dataset/biwi-kinect-head-pose","name":"Biwi Kinect Head Pose","full_name":"","num_papers_in_archive":7},{"url":"/dataset/hpd","name":"HPD","full_name":"Head-Pose Detection","num_papers_in_archive":4},{"url":"/dataset/dad-3dheads","name":"DAD-3DHeads","full_name":"DAD-3DHeads dataset","num_papers_in_archive":3},{"url":"/dataset/arkitface","name":"ARKitFace","full_name":"","num_papers_in_archive":2},{"url":"/dataset/ict-3dhp","name":"ICT-3DHP","full_name":"","num_papers_in_archive":0}],"subtasks":[],"parent_tasks":[{"url":"/task/pose-estimation","name":"Pose Estimation"}],"papers":{"order":"repositories listed in the archive (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":30,"of":55,"tagged_in_all":130,"items":[{"url":"/paper/fine-grained-head-pose-estimation-without","title":"Fine-Grained Head Pose Estimation Without Keypoints","date":"2017-10-02","arxiv_id":"1710.00925","repositories_listed":14,"syntology":{"n":3,"n_ran":3,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/how-far-are-we-from-solving-the-2d-3d-face","title":"How far are we from solving the 2D & 3D Face Alignment problem? (and a dataset of 230,000 3D facial landmarks)","date":"2017-03-21","arxiv_id":"1703.07332","repositories_listed":8,"syntology":{"n":15,"n_ran":4,"n_unverified":11,"n_pointer_only":0}},{"url":"/paper/synergy-between-3dmm-and-3d-landmarks-for","title":"Synergy between 3DMM and 3D Landmarks for Accurate 3D Facial Geometry","date":"2021-10-19","arxiv_id":"2110.09772","repositories_listed":4,"syntology":null},{"url":"/paper/whenet-real-time-fine-grained-estimation-for","title":"WHENet: Real-time Fine-Grained Estimation for Wide Range Head Pose","date":"2020-05-20","arxiv_id":"2005.10353","repositories_listed":4,"syntology":null},{"url":"/paper/detect-faces-efficiently-a-survey-and","title":"Detect Faces Efficiently: A Survey and Evaluations","date":"2021-12-03","arxiv_id":"2112.01787","repositories_listed":3,"syntology":null},{"url":"/paper/facexformer-a-unified-transformer-for-facial","title":"FaceXFormer: A Unified Transformer for Facial Analysis","date":"2024-03-19","arxiv_id":"2403.12960","repositories_listed":2,"syntology":null},{"url":"/paper/towards-robust-and-unconstrained-full-range","title":"Towards Robust and Unconstrained Full Range of Rotation Head Pose Estimation","date":"2023-09-14","arxiv_id":"2309.07654","repositories_listed":2,"syntology":null},{"url":"/paper/6d-rotation-representation-for-unconstrained","title":"6D Rotation Representation For Unconstrained Head Pose Estimation","date":"2022-02-25","arxiv_id":"2202.12555","repositories_listed":2,"syntology":{"n":8,"n_ran":5,"n_unverified":3,"n_pointer_only":3}},{"url":"/paper/mos-a-low-latency-and-lightweight-framework","title":"MOS: A Low Latency and Lightweight Framework for Face Detection, Landmark Localization, and Head Pose Estimation","date":"2021-10-21","arxiv_id":"2110.10953","repositories_listed":2,"syntology":null},{"url":"/paper/img2pose-face-alignment-and-detection-via","title":"img2pose: Face Alignment and Detection via 6DoF, Face Pose Estimation","date":"2020-12-14","arxiv_id":"2012.07791","repositories_listed":2,"syntology":null},{"url":"/paper/dctd-deep-conditional-target-densities-for","title":"Energy-Based Models for Deep Probabilistic Regression","date":"2019-09-26","arxiv_id":"1909.12297","repositories_listed":2,"syntology":null},{"url":"/paper/deep-label-distribution-learning-with-label","title":"Deep Label Distribution Learning with Label Ambiguity","date":"2016-11-06","arxiv_id":"1611.01731","repositories_listed":2,"syntology":null},{"url":"/paper/improve-impact-of-mobile-phones-on-remote","title":"A multimodal dataset for understanding the impact of mobile phones on remote online virtual education","date":"2024-12-13","arxiv_id":"2412.14195","repositories_listed":1,"syntology":null},{"url":"/paper/cascaded-multi-scale-attention-for-enhanced","title":"Cascaded Multi-Scale Attention for Enhanced Multi-Scale Feature Extraction and Interaction with Low-Resolution Images","date":"2024-12-03","arxiv_id":"2412.02197","repositories_listed":1,"syntology":null},{"url":"/paper/deep-learning-and-machine-learning-techniques","title":"Deep learning and machine learning techniques for head pose estimation: a survey","date":"2024-09-12","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/head-pose-estimation-based-on-5d-rotation","title":"Head Pose Estimation Based on 5D Rotation Representation","date":"2024-09-03","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/6dof-head-pose-estimation-through-explicit","title":"6DoF Head Pose Estimation through Explicit Bidirectional Interaction with Face Geometry","date":"2024-07-19","arxiv_id":"2407.14136","repositories_listed":1,"syntology":null},{"url":"/paper/on-the-power-of-data-augmentation-for-head","title":"On the power of data augmentation for head pose estimation","date":"2024-07-07","arxiv_id":"2407.05357","repositories_listed":1,"syntology":null},{"url":"/paper/semi-supervised-unconstrained-head-pose","title":"Semi-Supervised Unconstrained Head Pose Estimation in the Wild","date":"2024-04-03","arxiv_id":"2404.02544","repositories_listed":1,"syntology":null},{"url":"/paper/on-the-representation-and-methodology-for-1","title":"On the representation and methodology for wide and short range head pose estimation","date":"2024-01-11","arxiv_id":"2401.05807","repositories_listed":1,"syntology":null},{"url":"/paper/appearance-based-gaze-estimation-enhanced","title":"Appearance-based gaze estimation enhanced with synthetic images using deep neural networks","date":"2023-11-23","arxiv_id":"2311.14175","repositories_listed":1,"syntology":null},{"url":"/paper/2d-image-head-pose-estimation-via-latent","title":"2D Image head pose estimation via latent space regression under occlusion settings","date":"2023-11-10","arxiv_id":"2311.06038","repositories_listed":1,"syntology":null},{"url":"/paper/real-time-6dof-full-range-markerless-head","title":"Real-time 6DoF full-range markerless head pose estimation","date":"2023-11-07","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/dsfnet-dual-space-fusion-network-for-1","title":"DSFNet: Dual Space Fusion Network for Occlusion-Robust 3D Dense Face Alignment","date":"2023-05-19","arxiv_id":"2305.11522","repositories_listed":1,"syntology":null},{"url":"/paper/a-simple-baseline-for-direct-2d-multi-person","title":"DirectMHP: Direct 2D Multi-Person Head Pose Estimation with Full-range Angles","date":"2023-02-02","arxiv_id":"2302.01110","repositories_listed":1,"syntology":null},{"url":"/paper/domain-adaptation-for-head-pose-estimation","title":"Domain Adaptation for Head Pose Estimation Using Relative Pose Consistency","date":"2023-01-19","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/tokenhpe-learning-orientation-tokens-for","title":"TokenHPE: Learning Orientation Tokens for Efficient Head Pose Estimation via Transformers","date":"2023-01-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/ego-body-pose-estimation-via-ego-head-pose","title":"Ego-Body Pose Estimation via Ego-Head Pose Estimation","date":"2022-12-09","arxiv_id":"2212.04636","repositories_listed":1,"syntology":{"n":14,"n_ran":2,"n_unverified":12,"n_pointer_only":0}},{"url":"/paper/pose-disentangled-contrastive-learning-for","title":"Pose-disentangled Contrastive Learning for Self-supervised Facial Representation","date":"2022-11-24","arxiv_id":"2211.13490","repositories_listed":1,"syntology":null},{"url":"/paper/shape-preserving-facial-landmarks-with-graph","title":"Shape Preserving Facial Landmarks with Graph Attention Networks","date":"2022-10-13","arxiv_id":"2210.07233","repositories_listed":1,"syntology":null}],"syntology_records":4,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"}}