AI Paper Atlas

Research map / Point clouds / Segmentation and detection

PARTNER: Level up the Polar Representation for LiDAR 3D Object Detection

Ming Nie, Yujing Xue, Chunwei Wang, Chaoqiang Ye, Hang Xu, Xinge Zhu, Qingqiu Huang, Michael Bi Mi, Xinchao Wang, Li Zhang

ICCV 2023 · Point clouds › Segmentation and detection · approach: LiDAR voxel and pillar detectors · 21 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 global representation re-alignment (GRR) to polar detector (ablation)polar CenterPoint · Waymo val vehicleL1 mAP (%): 70.31 -> 72.62Improved
add geometry-aware adaptive (GA) module on top of GRR (ablation)PARTNER · Waymo val vehicleL1 mAP (%): 72.62 -> 75.35Improved
apply GRR to Cartesian detector (ablation)Cartesian CenterPoint · Waymo val vehicleL1 mAP (%): 73.51 -> 73.04Hurt
add auxiliary segmentation and regression losses only (ablation)GA module · Waymo val vehicleL1 mAP (%): 72.62 -> 72.48No clear effect
add geometric clues to attention (ablation)GA module · Waymo val vehicleL1 mAP (%): 74.34 -> 75.35Improved
use axial attention for re-alignment instead of GRR (ablation)polar detector · Waymo val vehicleL1 mAP (%): 73.33 -> 73.41No clear effect
use Swin or channel-wise attention for re-alignment instead of GRR (ablation)polar detector · Waymo val vehicleL1 mAP (%): 73.33 -> 73.62No clear effect
regress in polar coordinates instead of Cartesian (ablation)PARTNER · Waymo val vehicleL1 mAP (%): 75.35 -> 75.02Hurt
use SID or LID instead of uniform range partition (ablation)PARTNER · Waymo val vehicleL1 mAP (%): 75.35 -> 74.32Hurt
use polar instead of Cartesian voxels at coarse resolutionCenterPoint · Waymo val vehicle 5x voxel sizeL2 mAPH (%): 35.6 -> 46.0Improved
use polar instead of Cartesian voxels at fine resolutionCenterPoint · Waymo val vehicle 1x voxel sizeL2 mAPH (%): 65.5 -> 62.1Hurt
apply PARTNER on PointPillars for streaming detectionPolarStream · Waymo val streaming, 8 sectorsL2 mAP (%): 58.6 -> 63.1Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 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