AI Paper Atlas

Research map / 3D vision / Human pose estimation

Learning Visibility for Robust Dense Human Body Estimation

Chun-Han Yao, Jimei Yang, Duygu Ceylan, Yi Zhou, Yang Zhou, Ming-Hsuan Yang

ECCV 2022 · 3D vision › Human pose estimation · approach: Human shape and pose regression · 17 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 truncation modeling L_vis^{x,y} (ablation)VisDB mesh · 3DPWMPVE: 91.1 -> 85.5Improved
add occlusion modeling L_vis^z (ablation)VisDB mesh · 3DPWMPVE: 88.0 -> 85.5Improved
add depth ordering loss L_depth (ablation)VisDB mesh · 3DPWMPVE: 88.9 -> 85.5Improved
add UV correspondence loss L_uv (ablation)VisDB mesh · 3DPWMPVE: 87.1 -> 85.5Improved
add all four visibility/depth/UV components (ablation)I2L-MeshNet baseline · 3DPWMPJPE: 84.5 -> 73.5Improved
use dense visibility weighting in SMPL regression (ablation)VisDB SMPL · 3DPWMPVE: drops by 8.7mmImproved
add test-time optimization with visibility weighting (ablation)VisDB SMPL regression · 3DPWMPVE: further reduce the error by 3.8mmImproved
add optimization without visibility to regression without visibility (ablation)VisDB SMPL · 3DPWMPVE: 96.2 -> 93.9Improved
visibility-aware VisDB over retrained I2L-MeshNet baselineI2L-MeshNet · 3DPW-OCCMPVE: 120.2 -> 114.0Improved
visibility-aware VisDB over PAREPARE · 3DPWMPVE: 94.2 -> 83.5Improved
SMPL parameter output instead of mesh outputVisDB · 3DPWMPJPE: 73.5 -> 72.1Improved
VisDB (mesh) over Mesh GraphormerMesh Graphormer · Human3.6MPA-MPJPE: 34.5 -> 34.5No clear effect

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