AI Paper Atlas

Research map / 3D vision / Human pose estimation

Ray3D: Ray-Based 3D Human Pose Estimation for Monocular Absolute 3D Localization

Yu Zhan, Fenghai Li, Renliang Weng, Wongun Choi

CVPR 2022 · 3D vision › Human pose estimation · approach: Transformer-based multi-view 3D pose · 65 citations (OpenAlex)

Check 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
Use normalized 3D rays and camera embedding instead of the RIE baselineAbsolute 3D pose estimation · Human3.6M test with CPN-detected 2D keypointsAbs-MPJPE: 138.4 -> 109.5Improved
Use normalized 3D rays and camera embedding instead of the RIE baselineAbsolute 3D pose estimation · Human3.6M test with CPN-detected 2D keypointsMRPE: 129.6 -> 99.6Improved
Use Ray3D instead of PoseFormerAbsolute 3D pose estimation · 3DHP test with GT 2D keypointsAbs-MPJPE: 147.8 -> 103.4Improved
Use Ray3D instead of PoseFormerAbsolute 3D pose estimation · 3DHP test with GT 2D keypointsMRPE: 147.5 -> 95.8Improved
Add temporal input using 9 frames instead of a single frameRay3D · Human3.6M test with CPN-detected 2D keypointsAbs-MPJPE: 115.1 -> 109.5Mixed
Add intrinsic decoupling (ablation)RIE · Human3.6M train → 3DHP testMRPE: 1079.2 -> 448.9Improved
Add camera normalization after intrinsic decoupling (ablation)RIE with intrinsic decoupling · Human3.6M train → 3DHP testMRPE: 448.9 -> 311.6Improved
Add camera embedding (ablation)Ray3D without camera embedding · Human3.6M train → 3DHP testMRPE: 311.6 -> 307.4Improved
Use Ray3D instead of RIERoot-relative pose estimation · Human3.6M test with GT 2D keypointsMPJPE: 34.8 -> 34.4Improved
Convert pixel keypoints to normalized raysRay3D · Synthetic focal-length variationMRPEImproved
Add camera embedding to normalized-ray input (ablation)Ray3D without camera embedding · Synthetic camera extrinsic variationMRPEImproved
Use noisy camera pitch as inputRay3D · Human3.6M noisy-camera evaluationMPJPE: 81.2mm to 110.6mmHurt

Later papers that compared with this method

1 later accepted paper reports Ray3D as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

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