AI Paper Atlas

Research map / Point clouds / Segmentation and detection

LiDAR Distillation: Bridging the Beam-Induced Domain Gap for 3D Object Detection

Yi Wei, Zibu Wei, Yongming Rao, Jiaxin Li, Jie Zhou, Jiwen Lu

ECCV 2022 · Point clouds › Segmentation and detection · approach: LiDAR voxel and pillar detectors · 76 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 cloud density alignment (pseudo low-beam training data) (ablation)PointPillars · KITTI 32-beam target (moderate)AP_3D: 65.91 -> 67.01Improved
add knowledge distillation on top of density alignment (ablation)PointPillars · KITTI 32-beam target (moderate)AP_3D: 67.01 -> 70.15Improved
initialize student from pretrained teacher weights (ablation)PointPillars · KITTI 32-beam target (moderate)AP_3D: 69.01 -> 70.15Improved
use progressive 32-beam teacher instead of 64-beam teacher (ablation)PointPillars · KITTI 16-beam target (moderate)AP_3D: 58.80 -> 59.87Improved
use progressive 32-beam teacher instead of directly trained 32-beam teacher (ablation)PointPillars · KITTI 16-beam target (moderate)AP_3D: 58.74 -> 59.87Improved
mimic ROI regions instead of the whole BEV map (ablation)PointPillars · KITTI 32-beam target (moderate)AP_3D: 69.36 -> 70.15Improved
mimic ROI regions instead of groundtruth box regions only (ablation)PointPillars · KITTI 32-beam target (moderate)AP_3D: 69.99 -> 70.15Improved
use beam clustering downsampling instead of range-image interpolation upsampling (ablation)PointPillars · KITTI 32-beam target (moderate)AP_3D: 54.56 -> 70.15Improved
use downsampling instead of super-resolution upsampling (ablation)PointPillars · KITTI 32-beam target (moderate)AP_3D: 62.58 -> 70.15Improved
apply general UDA method ST3DPointPillars · KITTI 32-beam target (moderate)AP_3D: 65.91 -> 57.57Hurt
align source beams to 16* equivalent beams of target (ablation)SECOND-IoU · Waymo -> nuScenesAP_3D: 17.24 -> 22.86Improved
align source density to target (sacrifices source domain performance) (ablation)SECOND-IoU · Waymo (source domain)AP_3D: 54.01 -> 39.97Hurt

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