AI Paper Atlas

Research map / Point clouds / Segmentation and detection

PolarStream: Streaming Object Detection and Segmentation with Polar Pillars

Qi Chen, Sourabh Vora, Oscar Beijbom

NeurIPS 2021 · Point clouds › Segmentation and detection · approach: LiDAR voxel and pillar detectors · 18 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 bidirectional context padding (ablation)Polar Pillars streaming model · nuScenes val, 32 sectorsPQ: 60.3 -> 68.3Improved
Add bidirectional context padding (ablation)Polar Pillars streaming model · nuScenes val, 32 sectorsSegmentation mIoU: 67.1 -> 73.1Improved
Add bidirectional context padding (ablation)Polar Pillars streaming model · nuScenes val, 32 sectorsDetection mAP: 46.7 -> 52.4Improved
Add trailing-edge context padding (ablation)Polar Pillars streaming model · nuScenes val, 4 sectorsPQ: 67.7 -> 69Improved
Add trailing-edge context padding (ablation)Polar Pillars streaming model · nuScenes val, 2 sectorsDetection mAP: 52.1 -> 52.2No clear effect
Add range stratified convolution and normalization (ablation)Polar Pillars detector · nuScenes val, full sweepDetection mAP: 48.2 -> 49.1Improved
Add feature undistortion (ablation)Polar Pillars detector · nuScenes val, full sweepDetection mAP: 48.2 -> 48.6Improved
Add both range stratified convolution and normalization and feature undistortion (ablation)Polar Pillars detector · nuScenes val, full sweepDetection mAP: 48.2 -> 50.3Improved
Add range stratified convolution and normalization and feature undistortion (ablation)Cartesian Pillars detector · nuScenes val, full sweepDetection mAP: 50.6 -> 50.6No clear effect
Add joint semantic segmentation training (ablation)Polar Pillars detector with both polar-grid techniques · nuScenes val, full sweepDetection mAP: 50.3 -> 51.2Improved
Add joint semantic segmentation training (ablation)Cartesian Pillars · nuScenes val, full sweepSegmentation mIoU: 72.5 -> 72.1Hurt
Use streaming sectors rather than full-sweep inputPolar Pillars · nuScenes val, 2, 4, 8, and 16 sectorsDetection performanceImproved

Later papers that compared with this method

2 later accepted papers report PolarStream as a baseline in their results tables; 2 of them report a better number on most of the results they share with it.

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