AI Paper Atlas

Research map / 3D vision / 3D generation

LATR: 3D Lane Detection from Monocular Images with Transformer

Yueru Luo, Chaoda Zheng, Xu Yan, Tang Kun, Chao Zheng, Shuguang Cui, Zhen Li

ICCV 2023 · 3D vision › 3D generation · approach: 3D perception for autonomous driving · 76 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 learnable query embedding with lane-aware lane-level embedding from image features (ablation)LATR · OpenLane-300F1: 61.5 -> 70.4Improved
add dynamic 3D ground positional embedding (ablation)LATR with learnable queries · OpenLane-300F1: 45.5 -> 61.5Improved
add dynamic 3D ground positional embedding (ablation)LATR with lane-aware embedding · OpenLane-300F1: 67.9 -> 70.4Improved
add point-level embedding to lane-level queries (ablation)LATR · OpenLane-300F1: 66.5 -> 70.4Improved
use dynamic updated plane instead of fixed plane for 3D positions (ablation)LATR · OpenLane-300F1: 69.2 -> 70.4Improved
use plane rather than frustum to generate 3D positions (ablation)LATR · OpenLane-300F1: 69.1 -> 69.2Improved
add any 3D positional information to image pixels (ablation)LATR · OpenLane-300F1: 67.9 -> 69.1Improved
use six decoder layers instead of two (LATR vs LATR-Lite) (ablation)LATR · OpenLane valF1: 61.5 -> 61.9No clear effect
LATR versus previous best on challenging lighting scenariosLATR · OpenLane val, Extreme Weather and NightF1: +7.4 / +6.3Mixed
LATR versus previous best on OpenLane overallLATR · OpenLane valF1: 50.5 -> 61.9Improved
LATR versus PersFormer on ONCE-3DLanesLATR · ONCE-3DLanes valF1: 74.33 -> 80.59Improved

Later papers that compared with this method

9 later accepted papers report LATR as a baseline in their results tables; 8 of them report a better number on most of the results they share with it.

1 more not listed.

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