Research map / Detection and segmentation / CNN features
Geometric Constrained Joint Lane Segmentation and Lane Boundary Detection
Jie Zhang, Yi Xu, Bingbing Ni, Zhenyu Duan
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 |
|---|---|---|---|
| add structure loss functions to the multi-task network (ablation) | multi-task network · KITTI URBAN ROAD | IoU: 0.852 -> 0.861 | Improved |
| add inter-link encoder to the multi-task network (ablation) | multi-task network · KITTI URBAN ROAD | IoU: 0.852 -> 0.865 | Improved |
| add both inter-link encoder and structure loss (ablation) | multi-task network · KITTI URBAN ROAD | IoU: 0.852 -> 0.874 | Improved |
| add both inter-link encoder and structure loss (ablation) | multi-task network · KITTI URBAN ROAD | F1: 0.920 -> 0.933 | Improved |
| add structure loss on top of inter-link encoder (ablation) | inter-link network · KITTI lane boundary detection | F1: 0.788 -> 0.831 | Improved |
| add structure loss on top of inter-link encoder (ablation) | inter-link network · KITTI lane boundary detection | precision: 0.806 -> 0.838 | Improved |
| add structure loss on top of inter-link encoder (ablation) | inter-link network · KITTI lane boundary detection | recall: 0.771 -> 0.824 | Improved |
| add joint training of segmentation and boundary tasks | baseline segmentation · KITTI URBAN ROAD | IoU: 0.808 -> 0.852 | Improved |
| use the full model instead of Up-Conv-Poly | Ours · KITTI URBAN ROAD | IoU: 0.854 -> 0.874 | Improved |
| use the full model instead of Up-Conv-Poly | Ours · CULane lane segmentation | IoU: 0.807 -> 0.824 | Improved |
| use the full model instead of CMA | Ours · RVD Night | F1: 0.976 -> 0.988 | Improved |
| use the full model instead of SCNN for boundaries on No line scenes | Ours · CULane lane boundary detection (No line) | F1: 0.365 -> 0.351 | Hurt |
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.
- SegNet — SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation (TPAMI 2017) · better on 6 of 6 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
- Sketch and Refine: Towards Fast and Accurate Lane Detection (AAAI 2024 · similarity 0.89)
- LaneCPP: Continuous 3D Lane Detection using Physical Priors (CVPR 2024 · similarity 0.89)
- LaneSegNet: Map Learning with Lane Segment Perception for Autonomous Driving (ICLR 2024 · similarity 0.89)
- GEONet: Global Enhancement and Optimization Network for Lane Detection (AAAI 2025 · similarity 0.88)
- Rethinking Lanes and Points in Complex Scenarios for Monocular 3D Lane Detection (CVPR 2025 · similarity 0.88)
- A Hybrid Global-Local Perception Network for Lane Detection (AAAI 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.
