AI Paper Atlas

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

Rethinking IoU-Based Optimization for Single-Stage 3D Object Detection

Hualian Sheng, Sijia Cai, Na Zhao, Bing Deng, Jianqiang Huang, Xian-Sheng Hua, Min-Jian Zhao, Gim Hee Lee

ECCV 2022 · Detection and segmentation › 3D detection and driving · approach: Unified LiDAR 3D detection · 52 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 RDIoU losses (ablation)PointPillar · KITTI val Car Moderate3D R40 AP: 79.88 -> 82.42Improved
add RDIoU losses (ablation)SECOND · KITTI val Car Moderate3D R40 AP: 82.85 -> 85.80Improved
add RDIoU losses (ablation)CT-stacked · KITTI val Car Moderate3D R40 AP: 83.01 -> 86.20Improved
use RDIoU-guided instead of 3D IoU-guided IoU loss (ablation)CT-stacked · KITTI val Car Moderate3D R40 AP: 83.60 -> 85.73Improved
use RDIoU-guided instead of 3D IoU-guided DIoU loss (ablation)CT-stacked · KITTI val Car Moderate3D R40 AP: 84.20 -> 86.20Improved
use RDIoU-guided instead of 3D IoU-guided CIoU loss (ablation)CT-stacked · KITTI val Car Moderate3D R40 AP: 84.01 -> 85.98Improved
replace Smooth-l1 with 3D IoU-guided DIoU loss (ablation)CT-stacked · KITTI val Car Moderate3D R40 AP: 83.14 -> 84.20Improved
replace traditional focal loss with 3D IoU-guided QFL (ablation)CT-stacked · KITTI val Car Moderate3D R40 AP: 85.12 -> 85.79Improved
replace 3D IoU-guided QFL with RDIoU-guided QFL (ablation)CT-stacked · KITTI val Car Moderate3D R40 AP: 85.79 -> 86.20Improved
set rotation edge k to 1.0 rather than 0.6 (ablation)RDIoU · KITTI val Car Moderate3D R40 AP: 85.89 -> 86.20Improved
set k larger than 1.0 (1.8) (ablation)RDIoU · KITTI val Car Moderate3D R40 AP: 86.20 -> 85.59Hurt
use RDIoU instead of ODIoU (ablation)SECOND · KITTI val Car Moderate3D R40 AP: 83.88 -> 85.80Improved

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