AI Paper Atlas

Research map / 3D vision / 3D generation

ONCE-3DLanes: Building Monocular 3D Lane Detection

Fan Yan, Ming Nie, Xinyue Cai, Jianhua Han, Hang Xu, Zhen Yang, Chaoqiang Ye, Yanwei Fu, Michael Bi Mi, Li Zhang

CVPR 2022 · 3D vision › 3D generation · approach: 3D perception for autonomous driving · 81 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
Use SALAD instead of the strongest extended 2D baseline, LaneATT3D lane detection on ONCE-3DLanes · ONCE-3DLanes testF1(%): 56.57 -> 64.07Improved
Use SALAD instead of GenLaneNet3D lane detection on ONCE-3DLanes · ONCE-3DLanes testF1(%): 45.59 -> 64.07Improved
Use SALAD instead of 3D LaneNet3D lane detection on ONCE-3DLanes · ONCE-3DLanes testF1(%): 44.73 -> 64.07Improved
Add horizontal flip augmentation (ablation)SALAD · ONCE-3DLanes testF1(%): 61.18 -> 62.24 (+1.06)Improved
Add joint scale augmentation after flip (ablation)SALAD · ONCE-3DLanes testF1(%): 62.24 -> 64.07 (+1.83)Improved
Use smooth L1 rather than L1 regression loss (ablation)SALAD spatial contextual branch · ONCE-3DLanes testF1(%): 63.47 -> 64.07Improved
Use smooth L1 rather than L2 regression loss (ablation)SALAD spatial contextual branch · ONCE-3DLanes testF1(%): 62.91 -> 64.07Improved
Use SegFormer-B2 rather than Unet as backbone (ablation)SALAD · ONCE-3DLanes testF1(%): 61.12 -> 64.07Improved
Use SegFormer-B2 rather than Unet+self-att. as backbone (ablation)SALAD · ONCE-3DLanes testF1(%): 62.71 -> 64.07Improved
Use SegFormer-B2 rather than Unet+axial-att. as backbone (ablation)SALAD · ONCE-3DLanes testF1(%): 63.15 -> 64.07Improved
Use relative rather than absolute depth regression (ablation)SALAD spatial contextual branch · ONCE-3DLanes testF1(%): 62.37 -> 64.07Improved
Loosen the Chamfer Distance threshold from 0.15 to 0.30SALAD evaluation · ONCE-3DLanes testF1(%): 48.35 -> 64.07Improved

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