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
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 changed | Where | Measured | Effect |
|---|---|---|---|
| replace learnable query embedding with lane-aware lane-level embedding from image features (ablation) | LATR · OpenLane-300 | F1: 61.5 -> 70.4 | Improved |
| add dynamic 3D ground positional embedding (ablation) | LATR with learnable queries · OpenLane-300 | F1: 45.5 -> 61.5 | Improved |
| add dynamic 3D ground positional embedding (ablation) | LATR with lane-aware embedding · OpenLane-300 | F1: 67.9 -> 70.4 | Improved |
| add point-level embedding to lane-level queries (ablation) | LATR · OpenLane-300 | F1: 66.5 -> 70.4 | Improved |
| use dynamic updated plane instead of fixed plane for 3D positions (ablation) | LATR · OpenLane-300 | F1: 69.2 -> 70.4 | Improved |
| use plane rather than frustum to generate 3D positions (ablation) | LATR · OpenLane-300 | F1: 69.1 -> 69.2 | Improved |
| add any 3D positional information to image pixels (ablation) | LATR · OpenLane-300 | F1: 67.9 -> 69.1 | Improved |
| use six decoder layers instead of two (LATR vs LATR-Lite) (ablation) | LATR · OpenLane val | F1: 61.5 -> 61.9 | No clear effect |
| LATR versus previous best on challenging lighting scenarios | LATR · OpenLane val, Extreme Weather and Night | F1: +7.4 / +6.3 | Mixed |
| LATR versus previous best on OpenLane overall | LATR · OpenLane val | F1: 50.5 -> 61.9 | Improved |
| LATR versus PersFormer on ONCE-3DLanes | LATR · ONCE-3DLanes val | F1: 74.33 -> 80.59 | Improved |
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.
- SGC-Lane: Monocular 3D Lane Detection with Standard-Definition Map Guidance and Lane Completion (ECCV 2026 · better on 9 of 9 shared results)
- ReManNet: A Riemannian Manifold Network for Monocular 3D Lane Detection (CVPR 2026 · better on 2 of 2 shared results)
- HSDF-Lane: Height-Aligned Signed Distance Field with Semantic Lane Prior for 3D Lane Detection (ECCV 2026 · better on 1 of 1 shared result)
- SparseLaneSTP: Leveraging Spatio-Temporal Priors with Sparse Transformers for 3D Lane Detection (ICCV 2025 · better on 7 of 8 shared results)
- Rethinking Lanes and Points in Complex Scenarios for Monocular 3D Lane Detection (CVPR 2025 · better on 4 of 4 shared results)
- SC-Lane: Slope-aware and Consistent Road Height Estimation Framework for 3D Lane Detection (ICCV 2025 · better on 1 of 3 shared results)
- GLane3D: Detecting Lanes with Graph of 3D Keypoints (CVPR 2025 · better on 2 of 2 shared results)
- PVALane: Prior-Guided 3D Lane Detection with View-Agnostic Feature Alignment (AAAI 2024 · better on 2 of 2 shared results)
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
- Rethinking Lanes and Points in Complex Scenarios for Monocular 3D Lane Detection (CVPR 2025 · similarity 0.92)
- PVALane: Prior-Guided 3D Lane Detection with View-Agnostic Feature Alignment (AAAI 2024 · similarity 0.91)
- DV-3DLane: End-to-end Multi-modal 3D Lane Detection with Dual-view Representation (ICLR 2024 · similarity 0.90)
- LaneCPP: Continuous 3D Lane Detection using Physical Priors (CVPR 2024 · similarity 0.90)
- A Siamese Transformer with Hierarchical Refinement for Lane Detection (NeurIPS 2024 · similarity 0.89)
- GLane3D: Detecting Lanes with Graph of 3D Keypoints (CVPR 2025 · similarity 0.89)
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.
