AI Paper Atlas

Research map / 3D vision / Human pose estimation

Self-supervised Human Mesh Recovery with Cross-Representation Alignment

Xuan Gong, Meng Zheng, Benjamin Planche, Srikrishna Karanam, Terrence Chen, David Doermann, Ziyan Wu

ECCV 2022 · 3D vision › Human pose estimation · approach: Monocular 2D-to-3D pose lifting · 10 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
add IUV to 2D joints by input concatenation (ablation)CRA mesh regressor · 3DPW test (ablation, no refinement)PMPJPE (mm): 75.2 -> 60.1Improved
add 2D joints to IUV by input concatenation (ablation)CRA mesh regressor · 3DPW test (ablation, no refinement)PMPJPE (mm): 83.1 -> 60.1Improved
replace R1-only iterative regression with separate R1 and R2 regressors on global and fine-grained features (ablation)CRA mesh regressor · 3DPW test (ablation, no refinement)PMPJPE (mm): 61.0 -> 59.6Improved
add alignment feedback from the other representation (ablation)CRA mesh regressor · 3DPW test (ablation, no refinement)PMPJPE (mm): 59.6 -> 58.2Improved
add alignment feedback from both representations (ablation)CRA mesh regressor · 3DPW test (ablation, no refinement)PMPJPE (mm): 58.2 -> 56.3Improved
replace input concatenation with two-stream fusion plus full alignment (ablation)CRA mesh regressor · 3DPW test (ablation, no refinement)PMPJPE (mm): 60.1 -> 56.3Improved
add cross-representation alignment under heavy IUV occlusion (prob 0.9) (ablation)CRA mesh regressor · 3DPW test, IUV body-part occlusion prob 0.9PMPJPE (mm): 75.1 -> 60.6Improved
add cross-representation alignment under heavy IUV occlusion (prob 0.9), PVE (ablation)CRA mesh regressor · 3DPW test, IUV body-part occlusion prob 0.9PVE (mm): 160.3 -> 123.4Improved
add cross-representation alignment when 2D joints are removed with prob 0.9 (ablation)CRA mesh regressor · 3DPW test, 2D joints removal prob 0.9PMPJPE (mm): 156.3 -> 153.6Improved
add 2D joints to IUV under body-part occlusion prob 0.9, without CRA (ablation)CRA mesh regressor · 3DPW test, IUV body-part occlusion prob 0.9PMPJPE (mm): 109.1 -> 75.1Improved
add auxiliary refinement on in-the-wild images (3DPW)CRA mesh regressor · 3DPW testMPJPE (mm): 91.1 -> 89.1 MPJPE; 56.3 -> 55.9 PMPJPEImproved
add auxiliary refinement on Human3.6M Protocol 1CRA mesh regressor · Human3.6M Protocol #1MPJPE (mm): 87.1 -> 84.3Improved

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