AI Paper Atlas

Research map / 3D vision / Human pose estimation

Shape Prior Deformation for Categorical 6D Object Pose and Size Estimation

Meng Tian, Marcelo H Ang Jr, Gim Hee Lee

ECCV 2020 · 3D vision › Human pose estimation · approach: Instance-level 6D object pose · 240 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
regress NOCS coordinates directly instead of shape-deformation plus correspondence (ablation)Ours (RGB-D) · CAMERA25mAP 5deg 2cm: -3.1%Improved
regress NOCS coordinates directly instead of shape-deformation plus correspondence (ablation)Ours (RGB-D) · REAL275mAP 5deg 2cm: -5.6%Improved
add deformation regularization (ablation)Ours (RGB-D) · REAL275mAP 5deg 2cm: 19.3 -> 13.4Improved
add entropy regularization (ablation)Ours (RGB-D) · REAL275mAP 5deg 2cm: 19.3 -> 15.7Improved
add regularization losses (ablation)Ours (RGB-D) · CAMERA25mAP 5deg 2cm: 54.3 -> 53.9No clear effect
use learned categorical shape prior instead of sphere (no prior) (ablation)Ours (RGB-D) · REAL275mAP 5deg 2cm: 15.6 -> 19.3Improved
use learned categorical shape prior instead of sphere (no prior) (ablation)Ours (RGB-D) · CAMERA25mAP 5deg 2cm: 54.0 -> 54.3No clear effect
use mean latent embedding prior instead of random instance prior (ablation)Ours (RGB-D) · REAL275mAP 5deg 2cm: 17.9 -> 19.3Improved
use mean latent embedding prior instead of NN instance prior (ablation)Ours (RGB-D) · REAL275mAP 5deg 2cm: 17.0 -> 19.3Improved
add depth input to networkOurs (RGB-D) · CAMERA25mAP 5deg 2cm: 50.2 -> 54.3Improved
add depth input to networkOurs (RGB-D) · REAL275mAP 5deg 2cm: 15.7 -> 19.3Improved
deform shape prior instead of using it as is for reconstructionReconstruction network · CAMERA25 shape reconstructionChamfer distance x1e-3: 3.70 -> 1.97Improved

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