{"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/on-triangulation-as-a-form-of-self","title":"On Triangulation as a Form of Self-Supervision for 3D Human Pose Estimation","arxiv_id":"2203.15865","date":"2022-03-29","proceeding":null,"authors":["Soumava Kumar Roy","Leonardo Citraro","Sina Honari","Pascal Fua"],"abstract":"Supervised approaches to 3D pose estimation from single images are remarkably effective when labeled data is abundant. However, as the acquisition of ground-truth 3D labels is labor intensive and time consuming, recent attention has shifted towards semi- and weakly-supervised learning. Generating an effective form of supervision with little annotations still poses major challenge in crowded scenes. In this paper we propose to impose multi-view geometrical constraints by means of a weighted differentiable triangulation and use it as a form of self-supervision when no labels are available. We therefore train a 2D pose estimator in such a way that its predictions correspond to the re-projection of the triangulated 3D pose and train an auxiliary network on them to produce the final 3D poses. We complement the triangulation with a weighting mechanism that alleviates the impact of noisy predictions caused by self-occlusion or occlusion from other subjects. We demonstrate the effectiveness of our semi-supervised approach on Human3.6M and MPI-INF-3DHP datasets, as well as on a new multi-view multi-person dataset that features occlusion.","url_abs":"https://arxiv.org/abs/2203.15865v3","url_pdf":"https://arxiv.org/pdf/2203.15865v3.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-human-pose-estimation","task_name":"3D Human Pose Estimation"},{"task_slug":"3d-pose-estimation","task_name":"3D Pose Estimation"},{"task_slug":"form","task_name":"Form"},{"task_slug":"pose-estimation","task_name":"Pose Estimation"},{"task_slug":"weakly-supervised-3d-human-pose-estimation","task_name":"Weakly-supervised 3D Human Pose Estimation"},{"task_slug":"weakly-supervised-learning","task_name":"Weakly-supervised Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/weakly-supervised-3d-human-pose-estimation-on","task":"Weakly-supervised 3D Human Pose Estimation","dataset":"Human3.6M","model":"Triangulation","rank_in_archive_order":16,"of":33,"metrics":{"Average MPJPE (mm)":"64.7","PA-MPJPE":"52.1"},"uses_additional_data":false},{"leaderboard":"/sota/weakly-supervised-3d-human-pose-estimation-on-1","task":"Weakly-supervised 3D Human Pose Estimation","dataset":"MPI-INF-3DHP","model":"Triangulation","rank_in_archive_order":2,"of":3,"metrics":{"MPJPE":"118.4","PCK":"73.4"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2203.15865","atlas_url":"https://app.syntology.ai/?focus=2203.15865","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}