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 View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

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

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 11 code samples harvested from 1 repository linked to this paper: 9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code; here there are none.

By repository: community (archive-listed): 11 samples from 1 repository, 9 ran (9 with no instrument failure; 0 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Levels written between 2026-09-24 and 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

facebookresearch/sapiens mentioned on GitHubpytorchNOASSERTIONSyntology: not harvested report
ibaiGorordo/Sapiens-Pytorch-Inference pytorchMITSyntology: 11 samples, 9 ran (0 instrument-failed) · 2 unverified 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: 9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

9ran
2unverified

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. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (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 are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. 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 six 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; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. 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.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity.

ibaiGorordo/Sapiens-Pytorch-Inference community (archive-listed) 11 samples, 9 ran (0 instrument-failed) · 2 unverified
create_preprocessor sapiens_inference/common.py ran MIT (permissive) · c95b90559e24d797 · report fixture: signature input_size:tuple/1/int, mean:list/1/float, std:list/1/float · returned Compose · level recorded 2026-09-24
draw_depth_map sapiens_inference/depth.py ran fingerprinted MIT (permissive) · f8b5db3cb31556d8 · report fixture: signature depth_map:ndarray/2/float · returned ndarray · level recorded 2026-09-25
draw_normal_map sapiens_inference/normal.py ran fingerprinted MIT (permissive) · ec008328da6ade0d · report fixture: signature normal_map:ndarray/3/float · returned ndarray · level recorded 2026-09-24
expand_boxes in 5 papers sapiens_inference/predictor.py ran MIT (permissive) · e2ee7c364e6d3b69 · report fixture: signature boxes:ndarray/2/int, img_shape:tuple/1/int, padding:int/0/int · returned ndarray · level recorded 2026-09-24
filter_small_boxes sapiens_inference/predictor.py ran MIT (permissive) · 904ba61aa2f9ac03 · report fixture: signature boxes:ndarray/2/int, img_height:int/0/int, height_thres:float/0/float · returned ndarray · level recorded 2026-09-24
pose_estimation_preprocessor sapiens_inference/common.py ran MIT (permissive) · e95604d9afb269a8 · report fixture: signature input_size:tuple/1/int, mean:list/1/float, std:list/1/float · returned Compose · level recorded 2026-09-24
postprocess_depth sapiens_inference/depth.py ran MIT (permissive) · 6de6c934cc5a5872 · report fixture: signature results:Tensor/4/float, img_shape:tuple/1/int · returned ndarray · level recorded 2026-09-24
postprocess_normal sapiens_inference/normal.py ran MIT (permissive) · b8a82028e4aade65 · report fixture: signature results:Tensor/4/float, img_shape:tuple/1/int · returned ndarray · level recorded 2026-09-24
postprocess_segmentation sapiens_inference/segmentation.py ran MIT (permissive) · 251244b8c5d68a56 · report fixture: signature results:Tensor/4/float, img_shape:tuple/1/int · returned ndarray · level recorded 2026-09-24
download_hf_model sapiens_inference/common.py unverified MIT (permissive) · 95af9d8951a60dc5 · report
draw_boxes in 7 papers sapiens_inference/detector.py unverified MIT (permissive) · 43891ceb87a02a55 · 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