AI Paper Atlas

Research map / 3D vision / Human pose estimation

3D-Aware Neural Body Fitting for Occlusion Robust 3D Human Pose Estimation

Yi Zhang, Pengliang Ji, Angtian Wang, Jieru Mei, Adam Kortylewski, Alan Yuille

ICCV 2023 · 3D vision › Human pose estimation · approach: Monocular 2D-to-3D pose lifting · 44 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 NBV analysis-by-synthesis fitting on top of regression initialization (ablation)3DNBF · 3DPW-AdvOcc@80MPJPE: 171.4 -> 140.7Improved
use volumetric Neural Body Volumes instead of SMPL mesh representation (ablation)3DNBF · 3DPW-AdvOcc@80MPJPE: 146.6 -> 140.7Improved
add 3D-aware contrastive loss to feature extractor training (ablation)3DNBF · 3DPW-AdvOcc@80MPJPE: 167.4 -> 140.7Improved
use 4 pose-dependent features per kernel instead of 1 (pose-independent) (ablation)3DNBF · 3DPW-AdvOcc@80MPJPE: 189.6 -> 140.7Improved
increase pose-dependent features from 4 to 8 (ablation)3DNBF · 3DPW-AdvOcc@80MPJPE: 140.7 -> 161.2Hurt
replace regression baselines with 3DNBF on standard 3DPW3D human pose estimation · 3DPWMPJPE: 81.4 -> 79.8Improved
use 3DNBF refinement instead of EFT refinementHMR-EFT · 3DPW-AdvOcc@80MPJPE: 158.2 -> 150.2Improved
add SMPLify keypoint fitting to HMR-EFT on non-occluded 3DPWHMR-EFT · 3DPWMPJPE: 89.5 -> 106.2Hurt

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