Research map / Learning theory and algorithms / Clustering
Eigenlanes: Data-Driven Lane Descriptors for Structurally Diverse Lanes
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 data-driven curved lane candidates rather than straight-line candidates (ablation) | Lane candidate generation on SDLane · SDLane test, candidate generation | mIoU: 0.691 -> 0.814; 0.738 -> 0.814 | Helped |
| Cluster candidates in original lane space rather than eigenlane space (ablation) | Lane candidate generation on SDLane · SDLane test, candidate generation | mIoU: 0.814 -> 0.815 | No clear effect |
| Add regression offsets for lane refinement (ablation) | SIIC-Net · SDLane test | F-measure: 41.02 -> 80.47 | Helped |
| Use height classification to adjust lane endpoints (ablation) | SIIC-Net · SDLane test | F-measure: 75.08 -> 80.47 | Helped |
| Add the IC module and MWCS to SI and NMS (ablation) | SIIC-Net · SDLane test | F-measure: 78.69 -> 80.47 | Helped |
| Use ResNet18 rather than the full model's backbone (ablation) | Proposed method on CULane · CULane test, total | F-measure: 76.5 -> 77.2 | Hurt |
| Use the proposed detector rather than LaneATT | Lane detection · SDLane test | F-measure: 73.49 -> 80.47 | Helped |
| Use the proposed detector rather than LaneATT | Lane detection · CULane test, Curve | F-measure: 64.1 -> 62.9 | Hurt |
Closest papers by meaning
- Bezier Everywhere All at Once: Learning Drivable Lanes as Bezier Graphs (CVPR 2024 · similarity 0.87)
- GLane3D: Detecting Lanes with Graph of 3D Keypoints (CVPR 2025 · similarity 0.87)
- Sketch and Refine: Towards Fast and Accurate Lane Detection (AAAI 2024 · similarity 0.87)
- LaneSegNet: Map Learning with Lane Segment Perception for Autonomous Driving (ICLR 2024 · similarity 0.86)
- Rethinking Lanes and Points in Complex Scenarios for Monocular 3D Lane Detection (CVPR 2025 · similarity 0.86)
- Lane2Seq: Towards Unified Lane Detection via Sequence Generation (CVPR 2024 · similarity 0.86)
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.