Papers › Sapiens: Foundation for Human Vision Models

Sapiens: Foundation for Human Vision Models

22 Aug 2024arXiv:2408.12569archive 2025-07-28

Rawal Khirodkar, Timur Bagautdinov, Julieta Martinez, Su Zhaoen, Austin James, Peter Selednik, Stuart Anderson, Shunsuke Saito

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.

PaperPDFCodeCode Syntology ran

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2408.12569")

Code

Syntology Ran 0 of 11 code samples harvested from 1 repository linked to this paper; 11 have no recorded run.

By repository: community (archive-listed): 11 samples from 1 repository, 0 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

facebookresearch/sapiens mentioned on GitHubpytorchNOASSERTION report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

11 samples harvested; 0 ran; 0 honoured the contract we drafted; 11 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

11unverified

Licence: 0 of the 11 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from ibaiGorordo/Sapiens-Pytorch-Inference. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: 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. Samples from a repository marked official are listed first. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

create_preprocessor ibaiGorordo/Sapiens-Pytorch-Inference/sapiens_inference/common.py community (archive-listed) unverified MIT (permissive) · c95b90559e24d797 · report
download_hf_model ibaiGorordo/Sapiens-Pytorch-Inference/sapiens_inference/common.py community (archive-listed) unverified MIT (permissive) · 95af9d8951a60dc5 · report
draw_boxes ibaiGorordo/Sapiens-Pytorch-Inference/sapiens_inference/detector.py community (archive-listed) unverified MIT (permissive) · 43891ceb87a02a55 · report
draw_depth_map ibaiGorordo/Sapiens-Pytorch-Inference/sapiens_inference/depth.py community (archive-listed) unverified MIT (permissive) · f8b5db3cb31556d8 · report
draw_normal_map ibaiGorordo/Sapiens-Pytorch-Inference/sapiens_inference/normal.py community (archive-listed) unverified MIT (permissive) · ec008328da6ade0d · report
expand_boxes ibaiGorordo/Sapiens-Pytorch-Inference/sapiens_inference/predictor.py community (archive-listed) unverified MIT (permissive) · e2ee7c364e6d3b69 · report
filter_small_boxes ibaiGorordo/Sapiens-Pytorch-Inference/sapiens_inference/predictor.py community (archive-listed) unverified MIT (permissive) · 904ba61aa2f9ac03 · report
pose_estimation_preprocessor ibaiGorordo/Sapiens-Pytorch-Inference/sapiens_inference/common.py community (archive-listed) unverified MIT (permissive) · e95604d9afb269a8 · report
postprocess_depth ibaiGorordo/Sapiens-Pytorch-Inference/sapiens_inference/depth.py community (archive-listed) unverified MIT (permissive) · 6de6c934cc5a5872 · report
postprocess_normal ibaiGorordo/Sapiens-Pytorch-Inference/sapiens_inference/normal.py community (archive-listed) unverified MIT (permissive) · b8a82028e4aade65 · report
postprocess_segmentation ibaiGorordo/Sapiens-Pytorch-Inference/sapiens_inference/segmentation.py community (archive-listed) unverified MIT (permissive) · 251244b8c5d68a56 · report

Tasks

2D Human Pose Estimation2D Pose EstimationDepth EstimationHuman Part SegmentationKeypoint DetectionPose EstimationSurface Normal Estimation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
2D Human Pose Estimation COCO-WholeBody Sapiens-0.3B WB 62.0 #7 of 15 Archive leaderboard report
2D Human Pose Estimation COCO-WholeBody Sapiens-0.3B body 66.4 #7 of 15 Archive leaderboard report
2D Human Pose Estimation COCO-WholeBody Sapiens-0.3B face 87.1 #7 of 15 Archive leaderboard report
2D Human Pose Estimation COCO-WholeBody Sapiens-0.3B foot 67.3 #7 of 15 Archive leaderboard report
2D Human Pose Estimation COCO-WholeBody Sapiens-0.3B hand 58.1 #7 of 15 Archive leaderboard report
Keypoint Detection COCO (Common Objects in Context) Sapiens-2B Validation AP 82.2 #16 of 24 Archive leaderboard report
Keypoint Detection COCO (Common Objects in Context) Sapiens-1B Validation AP 82.1 #17 of 24 Archive leaderboard report
Keypoint Detection COCO (Common Objects in Context) Sapiens-0.6B Validation AP 81.2 #18 of 24 Archive leaderboard report
Keypoint Detection COCO (Common Objects in Context) Sapiens-0.3B Validation AP 79.6 #19 of 24 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

AttentionDense ConnectionsLayer NormalizationLinear LayerMulti-Head AttentionResidual ConnectionSETSoftmaxVision Transformer

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections