AI Paper Atlas

Research map / Detection and segmentation / 3D detection and driving

Correlation Field for Boosting 3D Object Detection in Structured Scenes

Jianhua Sun, Hao-Shu Fang, Xianghui Zhu, Jiefeng Li, Cewu Lu

AAAI 2022 · Detection and segmentation › 3D detection and driving · approach: Unified LiDAR 3D detection · 8 citations (OpenAlex)

Read the paper

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
Apply both CorrelaBoost strategies instead of vanilla augmentation (ablation)VoteNet · ScanNetV2mAP@0.5: 33.5 -> 41.2Improved
Apply both CorrelaBoost strategies instead of vanilla augmentation (ablation)VoteNet · SUN RGB-DmAP@0.5: 32.7 -> 37.7Improved
Add Category Consistent Exchanging (ablation)VoteNet · ScanNetV2mAP@0.5: 33.5 -> 36.9Improved
Add Energy Optimized Transformation (ablation)VoteNet · ScanNetV2mAP@0.5: 33.5 -> 38.8Improved
Add Category Consistent Exchanging (ablation)VoteNet · SUN RGB-DmAP@0.5: 32.7 -> 35.1Improved
Add Energy Optimized Transformation (ablation)VoteNet · SUN RGB-DmAP@0.5: 32.7 -> 36.3Improved
Use correlation-field-guided pasting rather than random pasteVoteNet · ScanNetV2mAP@0.5: 34.2 -> 41.2Improved
Use correlation-field-guided pasting rather than random pasteVoteNet · SUN RGB-DmAP@0.5: 33.6 -> 37.7Improved
Guide same-category exchanges with shape and orientation similarity rather than random pairing (ablation)VoteNet · ScanNetV2AP50: 35.5 -> 36.9Improved
Vary the shape and orientation similarity weights across the reported settings (ablation)VoteNet with exchanging only · ScanNetV2AP50: 35.5; 36.3; 36.7; 36.9; 36.6; 36.1Mixed
Vary correlation-field attenuation index gamma across the reported settings (ablation)VoteNet with transformation only · ScanNetV2AP50: 38.8; 38.6; 38.7Mixed
Vary correlation-field constant k across the reported settings (ablation)VoteNet with transformation only · ScanNetV2AP50: 38.4; 38.6; 38.3; 38.8Mixed

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