AI Paper Atlas

Research map / 3D vision / Human pose estimation

Category Level Object Pose Estimation via Neural Analysis-by-Synthesis

Xu Chen, Zijian Dong, Jie Song, Andreas Geiger, Otmar Hilliges

ECCV 2020 · 3D vision › Human pose estimation · approach: Category-level object pose estimation · 119 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 3D feature volume to the generator (ablation)pose-aware generator · ShapeNet pose fittingAP60: 90.2% -> 97.1%Improved
add 3D feature volume to the generator (ablation)pose-aware generator · ShapeNet pose fittingAP10: 1.8% -> 16.5%Improved
add KL divergence (VAE) training (ablation)pose-aware generator · ShapeNet pose fittingAP10: 12.3% -> 16.5%Improved
add KL divergence (VAE) training (ablation)pose-aware generator · ShapeNet pose fittingL1 reconstruction error: 0.049 -> 0.056Hurt
use 16-dim latent space instead of 4 (ablation)pose-aware generator · ShapeNet pose fittingAP10: 9.1% -> 16.5%Improved
use 16-dim latent space instead of 128 (ablation)pose-aware generator · ShapeNet pose fittingAP10: 11.4% -> 16.5%Improved
increase latent dimension from 16 to 128 (ablation)pose-aware generator · ShapeNet reconstructionL1 reconstruction error: 0.056 -> 0.041Improved
use perceptual loss instead of L1 energy (ablation)pose fitting · ShapeNet pose fittingAP60: 85.3% -> 97.1%Improved
use perceptual loss instead of L2 energy (ablation)pose fitting · ShapeNet pose fittingAP60: 88.3% -> 97.1%Improved
use perceptual loss instead of SSIM energy (ablation)pose fitting · ShapeNet pose fittingAP60: 92.5% -> 97.1%Improved
add latent-code regularization to the energy (ablation)pose fitting · ShapeNet pose fittingAP60: 95.9% -> 97.1%Improved

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