AI Paper Atlas

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

PillarNet: Real-Time and High-Performance Pillar-Based 3D Object Detection

Guangsheng Shi, Ruifeng Li, Chao Ma

ECCV 2022 · Detection and segmentation › 3D detection and driving · approach: Unified LiDAR 3D detection · 278 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
replace PointPillars encoder with PillarNet-18 sparse 2D conv encoderCenterPoint-PointPillars · nuScenes valmAP: +7.61% mAP and +5.94% NDSImproved
add dense-conv semantic stage-5 neck fusion (neckv2 over neckv1) (ablation)PillarNet-18 · nuScenes valNDS: 66.16 -> 66.41Improved
use neckv3 over neckv1 (ablation)PillarNet-18 · nuScenes valNDS: 66.16 -> 67.15Improved
use dense convolutions instead of sparse in neckv2 (neckv2-D) (ablation)PillarNet-18 · nuScenes valNDS: 66.41 -> 66.96Improved
add OD-DIoU regression loss (ablation)PillarNet-18 · nuScenes valmAP: +0.24% mAPImproved
add IoU-aware rectification (ablation)PillarNet-18 · nuScenes valmAP: +0.34%Improved
increase pillar size from 0.075m to 0.075*8m (ablation)PillarNet-18 · nuScenes valNDS: 67.15 -> 64.20Hurt
increase pillar size from 0.075m to 0.075*2m (ablation)PillarNet-18 · nuScenes valmAP: 59.48 -> 58.70Hurt
scale backbone from vgg to 34 (ablation)PillarNet · nuScenes valNDS: 65.71 -> 67.50Improved
use fine 0.075m pillars with lightweight PointPillars encoder (ablation)PointPillars · nuScenes valNDS: 60.22 -> 59.51Hurt
use two-frame input instead of single framePillarNet-18 · Waymo val Vehicle L2mAPH: 69.92 -> 71.08Improved
use two-frame input for cyclistPillarNet-34 · Waymo val Cyclist L1mAP: 72.29 -> 70.51Hurt

Later papers that compared with this method

1 later accepted paper reports PillarNet-34 as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

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