{"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/self-supervised-3d-hand-pose-estimation-from","title":"PeCLR: Self-Supervised 3D Hand Pose Estimation from monocular RGB via Equivariant Contrastive Learning","arxiv_id":"2106.05953","date":"2021-06-10","proceeding":"ICCV 2021 10","authors":["Adrian Spurr","Aneesh Dahiya","Xi Wang","Xucong Zhang","Otmar Hilliges"],"abstract":"Encouraged by the success of contrastive learning on image classification tasks, we propose a new self-supervised method for the structured regression task of 3D hand pose estimation. Contrastive learning makes use of unlabeled data for the purpose of representation learning via a loss formulation that encourages the learned feature representations to be invariant under any image transformation. For 3D hand pose estimation, it too is desirable to have invariance to appearance transformation such as color jitter. However, the task requires equivariance under affine transformations, such as rotation and translation. To address this issue, we propose an equivariant contrastive objective and demonstrate its effectiveness in the context of 3D hand pose estimation. We experimentally investigate the impact of invariant and equivariant contrastive objectives and show that learning equivariant features leads to better representations for the task of 3D hand pose estimation. Furthermore, we show that standard ResNets with sufficient depth, trained on additional unlabeled data, attain improvements of up to 14.5% in PA-EPE on FreiHAND and thus achieves state-of-the-art performance without any task specific, specialized architectures. Code and models are available at https://ait.ethz.ch/projects/2021/PeCLR/","url_abs":"https://arxiv.org/abs/2106.05953v5","url_pdf":"https://arxiv.org/pdf/2106.05953v5.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":"self-supervised-3d-hand-pose-estimation-from","repo_url":"https://github.com/dahiyaaneesh/peclr","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"self-supervised-3d-hand-pose-estimation-from","repo_url":"https://github.com/ut-vision/simhand","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"3d-hand-pose-estimation","task_name":"3D Hand Pose Estimation"},{"task_slug":"contrastive-learning","task_name":"Contrastive Learning"},{"task_slug":"hand-pose-estimation","task_name":"Hand Pose Estimation"},{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"pose-estimation","task_name":"Pose Estimation"},{"task_slug":"representation-learning","task_name":"Representation Learning"},{"task_slug":"translation","task_name":"Translation"},{"task_slug":"image-classification","task_name":"image-classification"}],"methods":[{"method_slug":"contrastive-learning","method_name":"Contrastive Learning"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/3d-hand-pose-estimation-on-freihand","task":"3D Hand Pose Estimation","dataset":"FreiHAND","model":"PeCLR","rank_in_archive_order":18,"of":33,"metrics":{"PA-MPJPE":"6.6"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2106.05953","atlas_url":"https://app.syntology.ai/?focus=2106.05953","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":"2106.05953"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2106.05953\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2106.05953"},"call":"get_concepts_for_paper(arxiv_id=\"2106.05953\")"}],"by_repo":[{"repo":"dahiyaaneesh/peclr","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"ut-vision/simhand","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2502.15251"],"harvested_for_calls":[{"arxiv_id":"2502.15251","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2502.15251"},"call":"get_harvested_code_for_paper(arxiv_id=\"2502.15251\")"}]}],"by_repo_harvested_for_is":"harvested_for: the arXiv ids (as Syntology's graph holds them) of every paper whose samples Syntology's graph links to this repository, in arXiv-id order, complete; the page names the first 3 and says how many more. A link only: it does not say the papers are the same work, that one copied the other, or that the code implements this paper's method; harvested_for_calls gives the get_harvested_code_for_paper call for each arXiv-shaped id among them","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":"4fecf861721bf0972a0f3e49ad7d0fffac98f5dbb22d23707e875fab72c84442","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}