AI Paper Atlas

Research map / 3D vision / Human pose estimation

Self-Supervised Category-Level 6D Object Pose Estimation with Deep Implicit Shape Representation

Wanli Peng, Jianhang Yan, Hongtao Wen, Yi Sun

AAAI 2022 · 3D vision › Human pose estimation · approach: Instance-level 6D object pose · 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
Add self-supervised training on real data (ablation)Ours · NOCS-REAL test10°10cm mAP (%): 9.15 -> 49.80Improved
Add image-flip data augmentation (ablation)Self-Sup · NOCS-REAL test10°10cm mAP (%): 49.80 -> 56.24Improved
Add chamfer loss (ablation)Self-supervised framework · NOCS-REAL testIoU50 mAP (%): 15.31 -> 19.62Improved
Add SDF alignment loss (ablation)Self-supervised framework · NOCS-REAL testIoU50 mAP (%): 13.81 -> 19.62Improved
Retain supervised synthetic-data loss during joint learning (ablation)Self-supervised framework · NOCS-REAL testIoU50 mAP (%): 11.70 -> 19.62Improved
Add ICP refinementOurs · NOCS-REAL test5°2cm mAP (%): 16.76 -> 28.60Improved
Add ICP refinementOurs · NOCS-REAL testIoU50 mAP (%): 72.95 -> 72.67Hurt
Use the proposed self-supervised framework instead of NOCSNOCS-REAL test · NOCS-REAL testIoU50 mAP (%): 47.23 -> 72.95Improved

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