AI Paper Atlas

Research map / 3D vision / Human pose estimation

Sapiens: Foundation for Human Vision Models

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

ECCV 2024 · 3D vision › Human pose estimation · approach: Heatmap and coordinate pose encoding · 218 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
pretrain on human images (Humans-300M) instead of same-size general images (ablation)Sapiens-0.3B · Humans-5K posemAP: 37.3 -> 47.0Improved
pretrain on human images instead of general images (ablation)Sapiens-0.3B · Humans-2K segmentationmIoU: 52.8 -> 66.5Improved
pretrain on human images instead of general images (ablation)Sapiens-0.3B · THuman2.0 depthRMSE: 0.347 -> 0.288Improved
pretrain on human images instead of general images (ablation)Sapiens-0.3B · Hi4D normalMean angular error (deg): 26.8 -> 21.8Improved
scale human pretraining data from 100M to 300M images (ablation)Sapiens-0.3B · Humans-5K posemAP: 43.6 -> 47.0Improved
scale general pretraining data from 100M to 300M images (ablation)Sapiens-0.3B · Humans-5K posemAP: 35.7 -> 37.3Improved
add pretraining versus random initialization (ablation)Sapiens-0.3B · Humans-2K segmentationmIoU: 40.3 -> 66.5Improved
scale model from 0.3B to 2B parameters (ablation)Sapiens · Humans-5K poseWhole-body AP: 53.4 -> 61.1Improved
scale model from 0.3B to 2B parameters (ablation)Sapiens · Humans-2K segmentationmIoU: 76.7 -> 81.2Improved
scale model from 0.3B to 2B parameters (ablation)Sapiens · Hi4D normalMedian angular error (deg): 9.59 (1B) vs 9.62 (2B)No clear effect
use Sapiens-2B depth versus DepthAnything on Hi4DSapiens-2B · Hi4D depthAbsRel: 0.036 vs 0.034 (DepthAny-B)Mixed

Later papers that compared with this method

5 later accepted papers report Sapiens 2B as a baseline in their results tables; 5 of them report a better number on most of the results they share with it.

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy