AI Paper Atlas

Research map / Point clouds / Segmentation and detection

Embracing Single Stride 3D Object Detector With Sparse Transformer

Lue Fan, Ziqi Pang, Tianyuan Zhang, Yu-Xiong Wang, Hang Zhao, Feng Wang, Naiyan Wang, Zhaoxiang Zhang

CVPR 2022 · Point clouds › Segmentation and detection · approach: LiDAR voxel and pillar detectors · 289 citations (OpenAlex)

Check 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
Reduce backbone strides from {1, 2, 4, 8} to {1, 2, 2, 2} (ablation)PointPillars on Waymo Open Dataset · Waymo Open Dataset validationvehicle AP: 63.66 -> 66.03Improved
Use single stride {1, 1, 1, 1} rather than {1, 2, 2, 2} (ablation)PointPillars on Waymo Open Dataset · Waymo Open Dataset validationvehicle AP: 66.03 -> 64.69Hurt
Add dilation 2 in the last two stages (ablation)Single-stride PointPillars · Waymo Open Dataset validationvehicle AP: 64.69 -> 66.26Improved
Add dilation 2 in the last two stages (ablation)Single-stride PointPillars · Waymo Open Dataset validationpedestrian AP: 64.32 -> 63.51Hurt
Use 5 × 5 kernels in the last two stages (ablation)Single-stride PointPillars · Waymo Open Dataset validationvehicle AP: 64.69 -> 66.42Improved
Use 5 × 5 kernels in the last two stages (ablation)Single-stride PointPillars · Waymo Open Dataset validationlatency: 185ms -> 340msHurt
Replace standard convolutions with submanifold sparse convolutions (ablation)PointPillars-SS · Waymo Open Dataset, 20% training datavehicle 3D AP: 64.69 -> 51.57Hurt
Increase sparse-convolution kernel size from 3 × 3 to 5 × 5 (ablation)SparsePillars-SS · Waymo Open Dataset, 20% training datavehicle 3D AP: 51.57 -> 55.40Improved
Increase sparse-convolution kernel size from 3 × 3 to 7 × 7 (ablation)SparsePillars-SS · Waymo Open Dataset, 20% training datavehicle 3D AP: 51.57 -> 56.77Improved
Increase regional grouping size from 3.20m to 3.84m (ablation)SST · Waymo Open Dataset, 20% training datavehicle LEVEL_1 AP: 66.9 -> 67.9Improved
Increase regional grouping size from 3.20m to 5.12m (ablation)SST · Waymo Open Dataset, 20% training datapedestrian LEVEL_1 AP: 70.4 -> 71.1Improved
Increase SRA block count from 5 to 7 (ablation)SST · Waymo Open Dataset, 20% training datavehicle LEVEL_1 AP: 67.7 -> 67.8No clear effect

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 0 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