AI Paper Atlas

Research map / 3D vision / 3D generation

Anchor3DLane: Learning To Regress 3D Anchors for Monocular 3D Lane Detection

Shaofei Huang, Zhenwei Shen, Zehao Huang, Zi-han Ding, Jiao Dai, Jizhong Han, Naiyan Wang, Si Liu

CVPR 2023 · 3D vision › 3D generation · approach: 3D perception for autonomous driving · 70 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
use 3D anchors sampled from FV features rather than BEV features (ablation)Anchor3DLane · OpenLane-300F1(%): 47.6 -> 53.1Improved
add iterative regression, increasing from 1 to 2 steps (ablation)Anchor3DLane · OpenLane-300F1(%): 54.8 -> 56.3Improved
increase iterative regression from 2 to 3 steps (ablation)Anchor3DLane · OpenLane-300F1(%): 56.3 -> 57.0Improved
add temporal context using weighted-sum fusion (ablation)Anchor3DLane · OpenLane-300F1(%): 54.8 -> 55.8Improved
use cross-frame attention instead of weighted-sum fusion (ablation)Anchor3DLane · OpenLane-300x err/F(m): 0.346 -> 0.330Improved
add equal-width constraint optimization (ablation)Anchor3DLane · OpenLane-300x err/F(m): 0.349 -> 0.337Improved
add equal-width constraint optimization (ablation)Anchor3DLane · OpenLane-300F1(%): 54.8 -> 55.0Improved
expand the temporal training-frame range from 3 to 7 frames (ablation)Anchor3DLane · OpenLane-300F1(%): 55.0 -> 56.1Improved
replace ResNet-18 with EfficientNet-B3 (ablation)Anchor3DLane · OpenLane validationF1(%): 53.1 -> 56.0Improved
use Anchor3DLane instead of PersFormer3D lane detection · ONCE-3DLanes validationF1(%): 74.33 -> 74.44Improved
add iterative regression to Anchor3DLane (ablation)Anchor3DLane · ONCE-3DLanes validationF1(%): 74.44 -> 74.87Improved
add temporal information with iterative regression (ablation)Anchor3DLane · OpenLane validationF1(%): 53.7 -> 54.3Improved

Later papers that compared with this method

4 later accepted papers report Anchor3DLane as a baseline in their results tables; 4 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