GroupLane：基于通道分组的端到端3D车道线检测
GroupLane: End-to-End 3D Lane Detection with Channel-wise Grouping
AI总结：
针对3D车道线检测的部署效率需求，提出基于通道分组与逐行分类的端到端全卷积检测器GroupLane，在多个基准上精度超越现有最优方法且效率大幅提升。
摘要：
受实际部署需求约束，效率对3D车道线检测至关重要。本文提出了一种简洁、快速的端到端检测器，同时仍能保持高检测精度。具体而言，我们设计了一组基于逐行分类的全卷积检测头。与以往同类方法不同，我们的检测头支持识别垂直和水平车道线。此外，我们的方法是首个在鸟瞰图中执行逐行分类的方法。在检测头中，我们将特征拆分为多个组，每组特征对应一个车道线实例。训练阶段，预测结果通过提出的单窗口一对一匹配与车道线标签关联以计算损失，推理阶段无需任何后处理操作。通过这种方式，我们提出的全卷积检测器GroupLane实现了类似DETR（检测Transformer）的端到端检测。在OpenLane、Once-3DLanes和OpenLane-Huawei三个真实世界3D车道线基准上进行评估，采用ConvNext-Base作为骨干网络的GroupLane在OpenLane验证集上的F1分数优于已发表的当前最优方法PersFormer 13.6%。此外，使用ResNet18的GroupLane仍比PersFormer的F1分数高4.9%，同时推理速度快近7倍，浮点运算量仅为后者的13.3%。
英文摘要：
Efficiency is quite important for 3D lane detection due to practical deployment demand. In this work, we propose a simple, fast, and end-to-end detector that still maintains high detection precision. Specifically, we devise a set of fully convolutional heads based on row-wise classification. In contrast to previous counterparts, ours supports recognizing both vertical and horizontal lanes. Besides, our method is the first one to perform row-wise classification in bird-eye-view. In the heads, we split feature into multiple groups and every group of feature corresponds to a lane instance. During training, the predictions are associated with lane labels using the proposed single-win one-to-one matching to compute loss, and no post-processing operation is demanded for inference. In this way, our proposed fully convolutional detector, GroupLane, realizes end-to-end detection like DETR. Evaluated on 3 real world 3D lane benchmarks, OpenLane, Once-3DLanes, and OpenLane-Huawei, GroupLane adopting ConvNext-Base as the backbone outperforms the published state-of-the-art PersFormer by 13.6% F1 score in the OpenLane validation set. Besides, GroupLane with ResNet18 still surpasses PersFormer by 4.9% F1 score, while the inference speed is nearly 7x faster and the FLOPs is only 13.3% of it.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
