AI Paper Atlas

Research map / Point clouds / Segmentation and detection

Weakly Supervised 3D Object Detection from Lidar Point Cloud

Qinghao Meng, Wenguan Wang, Tianfei Zhou, Jianbing Shen, Luc Van Gool, Dengxin Dai

ECCV 2020 · Point clouds › Segmentation and detection · approach: LiDAR voxel and pillar detectors · 130 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
use weak click annotation (500 scenes + 534 precise instances) instead of 500 fully labeled scenesPointRCNN · KITTI val Car 3D Box@0.7 ModerateAP: 65.50 -> 75.10Improved
use weak annotation instead of 500 fully labeled scenesPointPillars · KITTI val Car 3D Box@0.7 ModerateAP: 60.75 -> 75.10Improved
weak supervision (about 3% of precise instances) versus full supervision with 3,712 scenesPointRCNN · KITTI val Car 3D Box@0.7 ModerateAP: 77.67 -> 75.10Hurt
weak supervision vs full supervision on KITTI testSTD · KITTI test Car 3D Box@0.7 ModerateAP: 79.71 -> 69.64Hurt
train on pedestrians with 951 click-labeled scenes and 515 instancesweakly supervised detector · KITTI val Pedestrian 3D Box@0.5 ModerateAP: 61.06 -> 69.96Improved
add precise BEV annotations instead of weak click BEV (ablation)weakly supervised detector · KITTI val Car 3D Box@0.7 ModerateAP: 75.10 -> 75.13No clear effect
add more weakly labeled scenes (3,712) with 534 precise instances (ablation)weakly supervised detector · KITTI val Car 3D Box@0.7 ModerateAP: 75.10 -> 76.04Improved
add 1,852 weakly labeled scenes with 25% precise instances (ablation)weakly supervised detector · KITTI val Car 3D Box@0.7 ModerateAP: 75.10 -> 76.78Improved
add 3,712 weakly labeled scenes with 25% precise instances (ablation)weakly supervised detector · KITTI val Car 3D Box@0.7 ModerateAP: 75.10 -> 77.62Improved
train PointRCNN on our automatic labels instead of manual labelsPointRCNN · KITTI val Car 3D Box@0.7 ModerateAP: 77.67 -> 74.54Hurt
train PointRCNN on our active labels instead of manual labelsPointRCNN · KITTI val Car 3D Box@0.7 ModerateAP: 77.67 -> 76.08Hurt
train PointPillars on our active labels instead of manual labelsPointPillars · KITTI val Car 3D Box@0.7 ModerateAP: 76.07 -> 75.03Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 3 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