PytorchAutoDrive:基于PyTorch的分段模型(ERFNet、ENet、DeepLab、FCN等)和车道检测模型(SCNN、RESA、LSTR、LaneATT、BézierLaneNet等),提供快速训练、可视化、基准测试和部署帮助

culane 开源项目推荐(8 个)
culane 话题在 GitHub 上没有填写简介,这里按 Star 数汇总最相关的热门仓库。
热门项目 全部 8
GitHub 共 8 个仓库,已全部展示An open source lane detection toolbox based on PyTorch, including SCNN, RESA, UFLD, LaneATT, CondLane, etc.
Lane Detection in Low-light Conditions Using an Efficient Data Enhancement : Light Conditions Style Transfer (IV 2020)
An end-to-end pipeline, built from pre-trained models, to detect cars on lanes for images and videos.
This repository provides two deep learning pipelines for real-time scene analysis in Euro Truck Simulator 2. The first solution utilizes LaneNet with an ENet backbone for lane detection alongside Yolo11n for object detection. The second solution employs YOLOPv2 to simultaneously detect lanes and vehicles.
Lane detection prototype for ADAS: comparing classical CV (Canny/Hough, IPM + sliding window) vs deep learning (UFLD) on CULane, with full quantitative evaluation and error analysis.
An interactive interface to configure and generate CLI commands for lane detection experiments. Features real-time controls for synthetic distribution shifts (noise, rotation, shear) and dataset hyperparameters.
PyTorch version code of "DLFNet: Multi-Scale Dynamic Weighted Lane Feature Network for Complex Scenes"(ICIC2025).
关于这个话题
- 清单取自 GitHub 话题页并按 Star 数排序,每次展示前 8 个项目;原始页面见 https://github.com/topics/culane。
- 该话题在 GitHub 上共有 8 个仓库, 本站收录的是其中最热门的 8 个,不是全量列表。
- Star / Fork 每日自动刷新一次,实时数据以 GitHub 为准。
- 当前 8 个项目累计 1726 Star,覆盖 2 种主要语言,数据更新于 2026-11-08。
- 中文介绍来自 GitHub 官方话题说明(github/explore)的机器翻译,可点「查看原文」对照;译文缺失时会先展示原文。