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
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 |
|---|---|---|---|
| use 3D anchors sampled from FV features rather than BEV features (ablation) | Anchor3DLane · OpenLane-300 | F1(%): 47.6 -> 53.1 | Improved |
| add iterative regression, increasing from 1 to 2 steps (ablation) | Anchor3DLane · OpenLane-300 | F1(%): 54.8 -> 56.3 | Improved |
| increase iterative regression from 2 to 3 steps (ablation) | Anchor3DLane · OpenLane-300 | F1(%): 56.3 -> 57.0 | Improved |
| add temporal context using weighted-sum fusion (ablation) | Anchor3DLane · OpenLane-300 | F1(%): 54.8 -> 55.8 | Improved |
| use cross-frame attention instead of weighted-sum fusion (ablation) | Anchor3DLane · OpenLane-300 | x err/F(m): 0.346 -> 0.330 | Improved |
| add equal-width constraint optimization (ablation) | Anchor3DLane · OpenLane-300 | x err/F(m): 0.349 -> 0.337 | Improved |
| add equal-width constraint optimization (ablation) | Anchor3DLane · OpenLane-300 | F1(%): 54.8 -> 55.0 | Improved |
| expand the temporal training-frame range from 3 to 7 frames (ablation) | Anchor3DLane · OpenLane-300 | F1(%): 55.0 -> 56.1 | Improved |
| replace ResNet-18 with EfficientNet-B3 (ablation) | Anchor3DLane · OpenLane validation | F1(%): 53.1 -> 56.0 | Improved |
| use Anchor3DLane instead of PersFormer | 3D lane detection · ONCE-3DLanes validation | F1(%): 74.33 -> 74.44 | Improved |
| add iterative regression to Anchor3DLane (ablation) | Anchor3DLane · ONCE-3DLanes validation | F1(%): 74.44 -> 74.87 | Improved |
| add temporal information with iterative regression (ablation) | Anchor3DLane · OpenLane validation | F1(%): 53.7 -> 54.3 | Improved |
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.
- SGC-Lane: Monocular 3D Lane Detection with Standard-Definition Map Guidance and Lane Completion (ECCV 2026 · better on 1 of 1 shared result)
- Rethinking Lanes and Points in Complex Scenarios for Monocular 3D Lane Detection (CVPR 2025 · better on 1 of 1 shared result)
- Anchor3DLane++: 3D Lane Detection via Sample-Adaptive Sparse 3D Anchor Regression (TPAMI 2024 · better on 5 of 6 shared results)
- PVALane: Prior-Guided 3D Lane Detection with View-Agnostic Feature Alignment (AAAI 2024 · better on 1 of 1 shared result)
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
- Anchor3DLane++: 3D Lane Detection via Sample-Adaptive Sparse 3D Anchor Regression (TPAMI 2024 · similarity 0.97)
- PVALane: Prior-Guided 3D Lane Detection with View-Agnostic Feature Alignment (AAAI 2024 · similarity 0.91)
- Rethinking Lanes and Points in Complex Scenarios for Monocular 3D Lane Detection (CVPR 2025 · similarity 0.91)
- DV-3DLane: End-to-end Multi-modal 3D Lane Detection with Dual-view Representation (ICLR 2024 · similarity 0.90)
- GLane3D: Detecting Lanes with Graph of 3D Keypoints (CVPR 2025 · similarity 0.87)
- LaneCPP: Continuous 3D Lane Detection using Physical Priors (CVPR 2024 · similarity 0.87)
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.
