AI Paper Atlas

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

RangeDet: In Defense of Range View for LiDAR-Based 3D Object Detection

Lue Fan, Xuan Xiong, Feng Wang, Naiyan Wang, ZhaoXiang Zhang

ICCV 2021 · Detection and segmentation › 3D detection and driving · approach: Multi-camera BEV detection · 267 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 Meta-Kernel convolution (ablation)RangeDet baseline (A1) · WOD vehicle3D AP: 53.39 -> 56.58Improved
add Range Conditioned Pyramid (ablation)RangeDet baseline (A1) · WOD vehicle3D AP: 53.39 -> 58.37Improved
add IoU prediction head (ablation)RangeDet (Meta-Kernel + RCP) · WOD vehicle3D AP: 61.05 -> 64.61Improved
add weighted NMS (ablation)RangeDet (A5) · WOD vehicle3D AP: 64.61 -> 69.00Improved
add range-view data augmentation (ablation)RangeDet (A6) · WOD vehicle3D AP: 69.00 -> 72.85Improved
add Meta-Kernel (ablation)RangeDet · WOD pedestrian3D AP: 69.06 -> 74.16Improved
aggregate by concatenation instead of max-pooling (ablation)Meta-Kernel · WOD vehicle3D AP: 63.47 -> 67.37Improved
aggregate by concatenation instead of summation (ablation)Meta-Kernel · WOD vehicle3D AP: 63.52 -> 67.37Improved
generate kernel weights from relative pixel coordinates only (ablation)Meta-Kernel · WOD vehicle3D AP: 63.57 -> 63.87No clear effect
generate kernel weights from relative Cartesian coordinates (ablation)Meta-Kernel · WOD vehicle3D AP: 63.57 -> 67.00Improved
add relative range to relative Cartesian coordinates as meta-data (ablation)Meta-Kernel · WOD vehicle3D AP: 67.00 -> 67.37No clear effect
place Meta-Kernel at stride 1 instead of stride 8 (ablation)RangeDet · WOD vehicle3D AP: 63.80 -> 67.37Improved

Later papers that compared with this method

2 later accepted papers report RangeDet as a baseline in their results tables; 2 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 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