AI Paper Atlas

Research map / 3D vision / Human pose estimation

Shape-Constraint Recurrent Flow for 6D Object Pose Estimation

Yang Hai, Rui Song, Jiaojiao Li, Yinlin Hu

CVPR 2023 · 3D vision › Human pose estimation · approach: Instance-level 6D object pose · 29 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
constrain correlation lookup using pose-induced flow from the target's 3D shape (ablation)recurrent pose refinement with RANSAC-PnP · YCB-VADD-0.1d: 61.9 -> 67.6Improved
replace RANSAC-PnP with a learned pose regressor (ablation)recurrent pose refinement without shape-constraint lookup · YCB-VADD-0.1d: 61.9 -> 63.6Improved
add a learned pose regressor while retaining shape-constraint lookup (ablation)recurrent pose refinement · YCB-VADD-0.1d: 67.6 -> 70.5Improved
use more recurrent inference iterations (ablation)SCFlow · YCB-VADD-0.1d: over 11.5%Improved
train with mixed real and PBR data rather than real images alone (ablation)SCFlow · LINEMODADD-0.1d: 99.3 -> 99.3No clear effect
train with mixed real and PBR data rather than real images alone (ablation)SCFlow · LINEMOD-OccludedADD-0.1d: 66.4 -> 67.0Improved
train with mixed real and PBR data rather than real images alone (ablation)SCFlow · YCB-VADD-0.1d: 70.5 -> 73.2Improved
use shape-constraint recurrent refinement instead of PFAPoseCNN-initialized pose refinement · YCB-VADD-0.1d: 61.9 -> 70.5Improved
remove reliance on RANSAC-PnP through learned pose regressionpose refinement · YCB-Vrefinement time (ms): 37 -> 17Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 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