AI Paper Atlas

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

PersFormer: 3D Lane Detection via Perspective Transformer and the OpenLane Benchmark

Li Chen, Chonghao Sima, Yang Li, Zehan Zheng, Jiajie Xu, Xiangwei Geng, Hongyang Li, Conghui He, Jianping Shi, Yu Qiao, Junchi Yan

ECCV 2022 · Detection and segmentation › 3D detection and driving · approach: LiDAR perception for driving · 221 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 multi-task 2D detection head (ablation)3D-only baseline · OpenLane 300-segment subset3D F-Score: 41.77 -> 43.49Improved
add unified anchor design (ablation)3D-only baseline · OpenLane 300-segment subset3D F-Score: 41.77 -> 42.75Improved
add both unified anchor and multi-task (ablation)3D baseline · OpenLane 300-segment subset3D F-Score: 41.77 -> 44.29Improved
add unified anchor to multi-task 2D head (ablation)multi-task baseline · OpenLane 300-segment subset2D F-Score: 32.33 -> 34.98Improved
add Perspective Transformer (ablation)PersFormer with unified anchor · OpenLane 300-segment subset3D F-Score: 44.29 -> 46.62Improved
add Perspective Transformer (ablation)PersFormer with unified anchor · OpenLane 300-segment subset2D F-Score: 34.98 -> 37.00Improved
add auxiliary binary segmentation (ablation)PersFormer · OpenLane 300-segment subset3D F-Score: 46.62 -> 47.79Improved
add auxiliary binary segmentation (ablation)PersFormer · OpenLane 300-segment subset2D F-Score: 37.00 -> 42.00Improved
PersFormer vs best prior 3D method3D lane detection · OpenLane valF-Score: 44.1 -> 50.5Improved
PersFormer 2D head vs LaneATT baseline2D lane detection · OpenLane valF-Score: 31.0 -> 42.0Improved
PersFormer vs CondLaneNet-L in 2D2D lane detection · OpenLane valF-Score: 59.1 vs 42.0Hurt
unified anchor effect on x near errorPersFormer · OpenLane valX error near (m): 0.479 -> 0.485Hurt

Later papers that compared with this method

3 later accepted papers report PersFormer as a baseline in their results tables; 3 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