AI Paper Atlas

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

General Geometry-aware Weakly Supervised 3D Object Detection

Guowen Zhang, Junsong Fan, Liyi Chen, Zhaoxiang Zhang, Zhen Lei, Lei Zhang

ECCV 2024 · Detection and segmentation › 3D detection and driving · approach: Unified LiDAR 3D detection · 12 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 point-to-box alignment loss to BPL (ablation)GGA · KITTI val Car IoU=0.7 EasyAP: 7.92 -> 26.39Improved
add semantic ratio loss to BPL (ablation)GGA · KITTI val Car IoU=0.7 EasyAP: 7.92 -> 42.21Improved
add PAL to BPL+SRL (ablation)GGA · KITTI val Car IoU=0.7 EasyAP: 42.21 -> 56.02Improved
add SRL to BPL+PAL (ablation)GGA · KITTI val Car IoU=0.7 EasyAP: 26.39 -> 56.02Improved
use SRL or PAL without BPL (ablation)GGA · KITTI valconvergenceHurt
vary semantic ratio prior value from 1.9 to 2.9 (ablation)SRL · KITTI val Car IoU=0.7 EasyAP: 44.05 (2.8) to 56.02 (2.4)Mixed
train detectors on GGA pseudo-labels instead of WeakM3D (monocular)MonoDETR · KITTI val Car IoU=0.7 EasyAP3D: 17.06 -> 21.18Improved
GGA versus WeakMono3D on hard monocular samplesGGA · KITTI val Car IoU=0.5 HardAP BEV/AP3D: 40.07/36.34 vs 37.09/34.22Hurt
GGA 2D-box supervision versus full 3D-box supervision for LiDAR detectorPointRCNN · KITTI test BEV PedestrianAP BEV: 49.43 -> 12.07Hurt
GGA with 2D boxes versus 3D-box supervised DSS on SUN-RGBDFCAF3D · SUN-RGBD valmAP@0.25: 42.1 -> 48.5Improved

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