AI Paper Atlas

Research map / 3D vision / Human pose estimation

3D Pose Estimation and 3D Model Retrieval for Objects in the Wild

Alexander Grabner, Peter M. Roth, Vincent Lepetit

CVPR 2018 · 3D vision › Human pose estimation · approach: Category-level object pose estimation · 151 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
use ResNet instead of VGG as the pose-estimation backbone (ablation)pose estimation · Pascal3D+MedErr: 11.7 -> 10.9Improved
use ResNet instead of VGG as the pose-estimation backbone (ablation)pose estimation · Pascal3D+Acc_{π/6}: 0.8076 -> 0.8341Improved
add blur augmentation to ResNet training (ablation)pose estimation · Pascal3D+Acc_{π/6}: 0.8341 -> 0.8392Improved
add blur augmentation to ResNet training (ablation)pose estimation · Pascal3D+MedErr: 10.9 -> 10.9No clear effect
add blur augmentation to VGG training (ablation)pose estimation · Pascal3D+Acc_{π/6}: 0.8076 -> 0.8033Hurt
add blur augmentation to VGG training (ablation)pose estimation · Pascal3D+MedErr: 11.7 -> 11.6Improved
share one output layer across categories instead of using category-specific predictions (ablation)pose estimation · Pascal3D+MedErr: 10.9 -> 11.5Hurt
share one output layer across categories instead of using category-specific predictions (ablation)pose estimation · Pascal3D+Acc_{π/6}: 0.8392 -> 0.8133Hurt
use the predicted pose rather than a random pose for rendering (ablation)3D model retrieval · Pascal3D+ validationTop-1-Acc: 0.2250 -> 0.4600Improved
use the predicted pose rather than a canonical pose for rendering (ablation)3D model retrieval · Pascal3D+ validationTop-1-Acc: 0.2925 -> 0.4600Improved
use the ground-truth pose rather than the predicted pose for rendering (ablation)3D model retrieval · Pascal3D+ validationTop-1-Acc: 0.4600 -> 0.4967Improved
use offline pre-computed descriptors and the closest discretized pose rather than online rendering under the predicted pose (ablation)3D model retrieval · Pascal3D+ validationTop-1-Acc: 0.4600 -> 0.4375Hurt

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