AI Paper Atlas

Research map / 3D vision / Human pose estimation

CAPTRA: CAtegory-Level Pose Tracking for Rigid and Articulated Objects From Point Clouds

Yijia Weng, He Wang, Qiang Zhou, Yuzhe Qin, Yueqi Duan, Qingnan Fan, Baoquan Chen, Hao Su, Leonidas J. Guibas

ICCV 2021 · 3D vision › Human pose estimation · approach: Category-level pose estimation · 107 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 pose canonicalization (previous-frame pose) to CoordinateNet (ablation)CoordinateNet · NOCS-REAL2755deg5cm accuracy: 14.93 -> 46.74Improved
add RotationNet to canonicalized CoordinateNet (ablation)CAPTRA · NOCS-REAL2755deg5cm accuracy: 46.74 -> 62.16Improved
use RotationNet residual rotation regression instead of DSAC++ pose fitting (ablation)canonicalized CoordinateNet · NOCS-REAL2755deg5cm accuracy: 54.77 -> 62.16Improved
add CoordinateNet to canonicalized pose regression (instead of regressing scale and translation) (ablation)CAPTRA · NOCS-REAL2755deg5cm accuracy: 25.99 -> 62.16Improved
add scale, translation and corner pose losses (ablation)CAPTRA · NOCS-REAL2755deg5cm accuracy: 60.48 -> 62.16Improved
add RotationNet to canonicalized CoordinateNet (ablation)CAPTRA · SAPIEN articulated5deg5cm accuracy: 95.06 -> 98.35Improved
use RotationNet instead of DSAC++ pose fitting (ablation)canonicalized CoordinateNet · SAPIEN articulated5deg5cm accuracy: 95.68 -> 98.35Improved
add CoordinateNet to canonicalized pose regression (ablation)CAPTRA · SAPIEN articulated5deg5cm accuracy: 21.69 -> 98.35Improved
add scale, translation and corner pose losses (ablation)CAPTRA · SAPIEN articulated5deg5cm accuracy: 97.63 -> 98.35Improved
track scale instead of fixing the noisy initial scale (ablation)CAPTRA · SAPIEN articulatedmIoU: 71.70% -> 74.00% (scale error 1.09% -> 0.30%)Improved
track scale instead of fixing the noisy initial scale (ablation)CAPTRA · NOCS-REAL275 (excluding camera)mIoU: 73.43% -> 76.42%Improved
add ground-truth joint axis rotation projection at test time (ablation)CAPTRA · SAPIEN articulated5deg5cm accuracy: 98.35 -> 98.74No clear effect

Later papers that compared with this method

5 later accepted papers report CAPTRA as a baseline in their results tables; 5 of them report a better number on most of the results they share with it.

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