AI Paper Atlas

Research map / 3D vision / Human pose estimation

CATRE: Iterative Point Clouds Alignment for Category-Level Object Pose Refinement

Xingyu Liu, Gu Wang, Yi Li, Xiangyang Ji

ECCV 2022 · 3D vision › Human pose estimation · approach: Category-level object pose estimation · 39 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 mean shape prior instead of 3D bounding box (ablation)CATRE · REAL275 (SPD* init)5deg5cm accuracy: 47.2 -> 54.4Improved
use mean shape prior instead of 3D axes (ablation)CATRE · REAL275 (SPD* init)5deg5cm accuracy: 43.1 -> 54.4Improved
add focalization to origin (ablation)CATRE · REAL275 (SPD* init)5deg5cm accuracy: 47.5 -> 54.4Improved
add adaptive points sampling (ablation)CATRE · REAL275 (SPD* init)5deg5cm accuracy: 42.3 -> 54.4Improved
use PointNet instead of 3D-GCN (ablation)CATRE · REAL275 (SPD* init)5deg5cm accuracy: 43.4 -> 54.4Improved
add weight sharing between the two branches (ablation)CATRE · REAL275 (SPD* init)5deg5cm accuracy: 2.0 -> 54.4Improved
use disentangled heads instead of a single TS-Head style head (ablation)CATRE · REAL275 (SPD* init)5deg5cm accuracy: 46.2 -> 54.4Improved
use disentangled heads instead of a single Rot-Head style head (ablation)CATRE · REAL275 (SPD* init)5deg5cm accuracy: 50.0 -> 54.4Improved
add pose-matching loss L_pm (ablation)CATRE · REAL275 (SPD* init)5deg5cm accuracy: 50.7 -> 54.4Improved
add separate rotation, translation and size losses (ablation)CATRE · REAL275 (SPD* init)5deg5cm accuracy: 30.1 -> 54.4Improved
also feed MaxPool(F_p) to TS-Head (ablation)CATRE · REAL275 (SPD* init)5deg5cm accuracy: 54.4 -> 52.8Hurt
add occlusion to the input (ablation)CATRE · REAL275 (SPD* init)5deg5cm accuracy: 54.4 -> 38.6Hurt

Later papers that compared with this method

2 later accepted papers report CATRE as a baseline in their results tables; 0 of them report a better number on most of the results they share with it.

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 4 of 4 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