{"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/sapiens-foundation-for-human-vision-models","title":"Sapiens: Foundation for Human Vision Models","arxiv_id":"2408.12569","date":"2024-08-22","proceeding":null,"authors":["Rawal Khirodkar","Timur Bagautdinov","Julieta Martinez","Su Zhaoen","Austin James","Peter Selednik","Stuart Anderson","Shunsuke Saito"],"abstract":"We present Sapiens, a family of models for four fundamental human-centric vision tasks -- 2D pose estimation, body-part segmentation, depth estimation, and surface normal prediction. Our models natively support 1K high-resolution inference and are extremely easy to adapt for individual tasks by simply fine-tuning models pretrained on over 300 million in-the-wild human images. We observe that, given the same computational budget, self-supervised pretraining on a curated dataset of human images significantly boosts the performance for a diverse set of human-centric tasks. The resulting models exhibit remarkable generalization to in-the-wild data, even when labeled data is scarce or entirely synthetic. Our simple model design also brings scalability -- model performance across tasks improves as we scale the number of parameters from 0.3 to 2 billion. Sapiens consistently surpasses existing baselines across various human-centric benchmarks. We achieve significant improvements over the prior state-of-the-art on Humans-5K (pose) by 7.6 mAP, Humans-2K (part-seg) by 17.1 mIoU, Hi4D (depth) by 22.4% relative RMSE, and THuman2 (normal) by 53.5% relative angular error. Project page: https://about.meta.com/realitylabs/codecavatars/sapiens.","url_abs":"https://arxiv.org/abs/2408.12569v3","url_pdf":"https://arxiv.org/pdf/2408.12569v3.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":"sapiens-foundation-for-human-vision-models","repo_url":"https://github.com/facebookresearch/sapiens","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"sapiens-foundation-for-human-vision-models","repo_url":"https://github.com/ibaiGorordo/Sapiens-Pytorch-Inference","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"2d-human-pose-estimation","task_name":"2D Human Pose Estimation"},{"task_slug":"2d-pose-estimation","task_name":"2D Pose Estimation"},{"task_slug":"depth-estimation","task_name":"Depth Estimation"},{"task_slug":"human-part-segmentation","task_name":"Human Part Segmentation"},{"task_slug":"keypoint-detection","task_name":"Keypoint Detection"},{"task_slug":"pose-estimation","task_name":"Pose Estimation"},{"task_slug":"surface-normal-estimation","task_name":"Surface Normal Estimation"}],"methods":[{"method_slug":"attention","method_name":"Attention"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"set","method_name":"SET"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"vision-transformer","method_name":"Vision Transformer"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/2d-human-pose-estimation-on-coco-wholebody-1","task":"2D Human Pose Estimation","dataset":"COCO-WholeBody","model":"Sapiens-0.3B","rank_in_archive_order":7,"of":15,"metrics":{"WB":"62.0","body":"66.4","face":"87.1","foot":"67.3","hand":"58.1"},"uses_additional_data":true},{"leaderboard":"/sota/keypoint-detection-on-coco","task":"Keypoint Detection","dataset":"COCO (Common Objects in Context)","model":"Sapiens-2B","rank_in_archive_order":16,"of":24,"metrics":{"Validation AP":"82.2"},"uses_additional_data":true},{"leaderboard":"/sota/keypoint-detection-on-coco","task":"Keypoint Detection","dataset":"COCO (Common Objects in Context)","model":"Sapiens-1B","rank_in_archive_order":17,"of":24,"metrics":{"Validation AP":"82.1"},"uses_additional_data":true},{"leaderboard":"/sota/keypoint-detection-on-coco","task":"Keypoint Detection","dataset":"COCO (Common Objects in Context)","model":"Sapiens-0.6B","rank_in_archive_order":18,"of":24,"metrics":{"Validation AP":"81.2"},"uses_additional_data":true},{"leaderboard":"/sota/keypoint-detection-on-coco","task":"Keypoint Detection","dataset":"COCO (Common Objects in Context)","model":"Sapiens-0.3B","rank_in_archive_order":19,"of":24,"metrics":{"Validation AP":"79.6"},"uses_additional_data":true}],"syntology":{"syntology_url":"https://syntology.ai/paper/2408.12569","atlas_url":"https://app.syntology.ai/?focus=2408.12569","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.12569"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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/ibaiGorordo/Sapiens-Pytorch-Inference","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/facebookresearch/sapiens","reach":{"status":"ok","spdx":"NOASSERTION"}}],"summary":{"ran":9,"unverified":2},"by_repo_kind":{"listed":{"samples":11,"ran":9,"repositories":1}},"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":"c95b90559e24d797","entry":"create_preprocessor","repo":"ibaiGorordo/Sapiens-Pytorch-Inference","repo_kind":"listed","path":"sapiens_inference/common.py","file_url":"https://github.com/ibaiGorordo/Sapiens-Pytorch-Inference/blob/HEAD/sapiens_inference/common.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":"c95b90559e24d797"}},{"code_sha256_prefix":"f8b5db3cb31556d8","entry":"draw_depth_map","repo":"ibaiGorordo/Sapiens-Pytorch-Inference","repo_kind":"listed","path":"sapiens_inference/depth.py","file_url":"https://github.com/ibaiGorordo/Sapiens-Pytorch-Inference/blob/HEAD/sapiens_inference/depth.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":"f8b5db3cb31556d8"}},{"code_sha256_prefix":"ec008328da6ade0d","entry":"draw_normal_map","repo":"ibaiGorordo/Sapiens-Pytorch-Inference","repo_kind":"listed","path":"sapiens_inference/normal.py","file_url":"https://github.com/ibaiGorordo/Sapiens-Pytorch-Inference/blob/HEAD/sapiens_inference/normal.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":"ec008328da6ade0d"}},{"code_sha256_prefix":"e2ee7c364e6d3b69","entry":"expand_boxes","repo":"ibaiGorordo/Sapiens-Pytorch-Inference","repo_kind":"listed","path":"sapiens_inference/predictor.py","file_url":"https://github.com/ibaiGorordo/Sapiens-Pytorch-Inference/blob/HEAD/sapiens_inference/predictor.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":"e2ee7c364e6d3b69"}},{"code_sha256_prefix":"904ba61aa2f9ac03","entry":"filter_small_boxes","repo":"ibaiGorordo/Sapiens-Pytorch-Inference","repo_kind":"listed","path":"sapiens_inference/predictor.py","file_url":"https://github.com/ibaiGorordo/Sapiens-Pytorch-Inference/blob/HEAD/sapiens_inference/predictor.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":"904ba61aa2f9ac03"}},{"code_sha256_prefix":"e95604d9afb269a8","entry":"pose_estimation_preprocessor","repo":"ibaiGorordo/Sapiens-Pytorch-Inference","repo_kind":"listed","path":"sapiens_inference/common.py","file_url":"https://github.com/ibaiGorordo/Sapiens-Pytorch-Inference/blob/HEAD/sapiens_inference/common.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":"e95604d9afb269a8"}},{"code_sha256_prefix":"6de6c934cc5a5872","entry":"postprocess_depth","repo":"ibaiGorordo/Sapiens-Pytorch-Inference","repo_kind":"listed","path":"sapiens_inference/depth.py","file_url":"https://github.com/ibaiGorordo/Sapiens-Pytorch-Inference/blob/HEAD/sapiens_inference/depth.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":"6de6c934cc5a5872"}},{"code_sha256_prefix":"b8a82028e4aade65","entry":"postprocess_normal","repo":"ibaiGorordo/Sapiens-Pytorch-Inference","repo_kind":"listed","path":"sapiens_inference/normal.py","file_url":"https://github.com/ibaiGorordo/Sapiens-Pytorch-Inference/blob/HEAD/sapiens_inference/normal.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":"b8a82028e4aade65"}},{"code_sha256_prefix":"251244b8c5d68a56","entry":"postprocess_segmentation","repo":"ibaiGorordo/Sapiens-Pytorch-Inference","repo_kind":"listed","path":"sapiens_inference/segmentation.py","file_url":"https://github.com/ibaiGorordo/Sapiens-Pytorch-Inference/blob/HEAD/sapiens_inference/segmentation.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":"251244b8c5d68a56"}},{"code_sha256_prefix":"95af9d8951a60dc5","entry":"download_hf_model","repo":"ibaiGorordo/Sapiens-Pytorch-Inference","repo_kind":"listed","path":"sapiens_inference/common.py","file_url":"https://github.com/ibaiGorordo/Sapiens-Pytorch-Inference/blob/HEAD/sapiens_inference/common.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":"95af9d8951a60dc5"}},{"code_sha256_prefix":"43891ceb87a02a55","entry":"draw_boxes","repo":"ibaiGorordo/Sapiens-Pytorch-Inference","repo_kind":"listed","path":"sapiens_inference/detector.py","file_url":"https://github.com/ibaiGorordo/Sapiens-Pytorch-Inference/blob/HEAD/sapiens_inference/detector.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":"43891ceb87a02a55"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}