AI Paper Atlas

Research map / Detection and segmentation / Open-set and few-shot detection

Normalized Object Coordinate Space for Category-Level 6D Object Pose and Size Estimation

He Wang, Srinath Sridhar, Jingwei Huang, Julien Valentin, Shuran Song, Leonidas J. Guibas

CVPR 2019 · Detection and segmentation › Open-set and few-shot detection · approach: Object-level representation learning · 781 citations (OpenAlex)

Check 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
predict dense NOCS maps and fit them to the depth point cloud instead of aligning a masked point cloud to a category model6D pose and size estimation · REAL275mAP 3D IoU@50%: 43.8% -> 76.4%Improved
predict dense NOCS maps and fit them to the depth point cloud instead of aligning a masked point cloud to a category model6D pose and size estimation · REAL275mAP (5°, 5 cm): 0.8% -> 10.2%Improved
add real-world training data and COCO images to CAMERA* training (ablation)NOCS regression network · REAL275mAP 3D IoU@50%: 36.7 -> 72.4Improved
add real-world training data and COCO images to CAMERA* training (ablation)NOCS regression network · REAL275mAP (5°, 5 cm): 3.4 -> 8.1Improved
add COCO to CAMERA* training data (ablation)NOCS regression network · REAL275mAP (5°, 5 cm): 3.4 -> 3.3No clear effect
replace context-aware CAMERA* compositing with non-context-aware compositing (ablation)NOCS regression network · REAL275mAP 3D IoU@50%: 72.4 -> 71.7Hurt
replace context-aware CAMERA* compositing with non-context-aware compositing (ablation)NOCS regression network · REAL275mAP (5°, 5 cm): 8.1 -> 7.9Hurt
use pixel classification instead of regression for NOCS prediction (ablation)NOCS prediction network · CAMERA25mAP (5°, 5 cm): 29.2 -> 40.9Improved
use pixel classification instead of regression for NOCS prediction (ablation)NOCS prediction network · REAL275mAP (5°, 5 cm): 8.1 -> 10.0Improved
use 128 bins instead of 32 bins (ablation)NOCS classification network · CAMERA25mAP 3D IoU@50%: 83.9 -> 85.3Improved
use 128 bins instead of 32 bins (ablation)NOCS classification network · CAMERA25mAP (5°, 5 cm): 40.9 -> 38.8Hurt
use 128 bins instead of 32 bins (ablation)NOCS classification network · REAL275mAP 3D IoU@50%: 78.0 -> 80.5Improved

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