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.

我们提出了一个简单、快速且端到端的检测器，旨在提高三维车道检测的效率，同时保持高的检测精度。我们的方法采用基于行级别分类的全卷积头部，支持识别垂直和水平车道，并首次在鸟瞰图中进行行级别分类。我们将特征分为多组，并且每组特征对应一个车道实例。通过使用单盈余一对一匹配将预测结果与车道标签相关联来计算损失，在推理过程中不需要后处理操作。我们的全卷积检测器 ConvNext-Base 作为骨干网络，在三个真实世界的三维车道基准 OpenLane、Once-3DLanes 和 OpenLane-Huawei 上进行评估，在 OpenLane 验证集中，GroupLane 的 F1 得分比最先进的 PersFormer 高出 13.6%，而使用 ResNet18 的 GroupLane 的 F1 得分仍然高于 PersFormer 4.9%，同时推理速度快近 7 倍，而 FLOPs 仅为其 13.3%。