{"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/learning-3d-human-pose-estimation-from-dozens","title":"Learning 3D Human Pose Estimation from Dozens of Datasets using a Geometry-Aware Autoencoder to Bridge Between Skeleton Formats","arxiv_id":"2212.14474","date":"2022-12-29","proceeding":null,"authors":["István Sárándi","Alexander Hermans","Bastian Leibe"],"abstract":"Deep learning-based 3D human pose estimation performs best when trained on large amounts of labeled data, making combined learning from many datasets an important research direction. One obstacle to this endeavor are the different skeleton formats provided by different datasets, i.e., they do not label the same set of anatomical landmarks. There is little prior research on how to best supervise one model with such discrepant labels. We show that simply using separate output heads for different skeletons results in inconsistent depth estimates and insufficient information sharing across skeletons. As a remedy, we propose a novel affine-combining autoencoder (ACAE) method to perform dimensionality reduction on the number of landmarks. The discovered latent 3D points capture the redundancy among skeletons, enabling enhanced information sharing when used for consistency regularization. Our approach scales to an extreme multi-dataset regime, where we use 28 3D human pose datasets to supervise one model, which outperforms prior work on a range of benchmarks, including the challenging 3D Poses in the Wild (3DPW) dataset. Our code and models are available for research purposes.","url_abs":"https://arxiv.org/abs/2212.14474v1","url_pdf":"https://arxiv.org/pdf/2212.14474v1.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":"learning-3d-human-pose-estimation-from-dozens","repo_url":"https://github.com/isarandi/metrabs","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"learning-3d-human-pose-estimation-from-dozens","repo_url":"https://github.com/isarandi/posepile","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"3d-human-pose-estimation","task_name":"3D Human Pose Estimation"},{"task_slug":"dimensionality-reduction","task_name":"Dimensionality Reduction"},{"task_slug":"pose-estimation","task_name":"Pose Estimation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2212.14474","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2212.14474"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/isarandi/metrabs","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/isarandi/posepile","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":2,"unverified":6},"by_repo_kind":{"listed":{"samples":8,"ran":2,"repositories":2}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"2f6a6eccfb577d4a","entry":"fixed_padding_layer","repo":"isarandi/metrabs","repo_kind":"listed","path":"metrabs_pytorch/backbones/efficientnet.py","file_url":"https://github.com/isarandi/metrabs/blob/HEAD/metrabs_pytorch/backbones/efficientnet.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"2f6a6eccfb577d4a"}},{"code_sha256_prefix":"697f5aa8d9395594","entry":"rearrange_tf_to_pt","repo":"isarandi/metrabs","repo_kind":"listed","path":"metrabs_pytorch/convert_model_from_tf.py","file_url":"https://github.com/isarandi/metrabs/blob/HEAD/metrabs_pytorch/convert_model_from_tf.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"697f5aa8d9395594"}},{"code_sha256_prefix":"65506ac65d5fefd7","entry":"get_joint2bone_mat","repo":"isarandi/posepile","repo_kind":"listed","path":"src/posepile/joint_info.py","file_url":"https://github.com/isarandi/posepile/blob/HEAD/src/posepile/joint_info.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"65506ac65d5fefd7"}},{"code_sha256_prefix":"9f844d1da50ec728","entry":"get_z","repo":"isarandi/posepile","repo_kind":"listed","path":"src/posepile/compositing.py","file_url":"https://github.com/isarandi/posepile/blob/HEAD/src/posepile/compositing.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"9f844d1da50ec728"}},{"code_sha256_prefix":"a019fdb41511cf6c","entry":"mean_stdev_masked","repo":"isarandi/metrabs","repo_kind":"listed","path":"metrabs_pytorch/ptu.py","file_url":"https://github.com/isarandi/metrabs/blob/HEAD/metrabs_pytorch/ptu.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a019fdb41511cf6c"}},{"code_sha256_prefix":"11ac9049df0417ee","entry":"reduce_mean_masked","repo":"isarandi/metrabs","repo_kind":"listed","path":"metrabs_pytorch/ptu.py","file_url":"https://github.com/isarandi/metrabs/blob/HEAD/metrabs_pytorch/ptu.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"11ac9049df0417ee"}},{"code_sha256_prefix":"c4919f8033efe728","entry":"reduce_sum_masked","repo":"isarandi/metrabs","repo_kind":"listed","path":"metrabs_pytorch/ptu.py","file_url":"https://github.com/isarandi/metrabs/blob/HEAD/metrabs_pytorch/ptu.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"c4919f8033efe728"}},{"code_sha256_prefix":"7766e0fe4266257a","entry":"to_homogeneous","repo":"isarandi/metrabs","repo_kind":"listed","path":"metrabs_pytorch/ptu3d.py","file_url":"https://github.com/isarandi/metrabs/blob/HEAD/metrabs_pytorch/ptu3d.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"7766e0fe4266257a"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}