DiffusionLane: Diffusion Model for Lane Detection

TL;DR

DiffusionLane introduces a diffusion-based approach for lane detection, leveraging a denoising process in parameter space and hybrid decoding to improve accuracy and generalization across multiple benchmarks.

Contribution

The paper proposes a novel diffusion model for lane detection with a hybrid decoder and auxiliary supervision, achieving state-of-the-art results on four benchmarks.

Findings

Outperforms previous methods on Carlane, Tusimple, CULane, LLAMAS.

Achieves over 81 ext{F1} score on CULane with MobileNetV4.

Surpasses existing methods by at least 1 ext{accuracy} on Carlane.

Abstract

In this paper, we present a novel diffusion-based model for lane detection, called DiffusionLane, which treats the lane detection task as a denoising diffusion process in the parameter space of the lane. Firstly, we add the Gaussian noise to the parameters (the starting point and the angle) of ground truth lanes to obtain noisy lane anchors, and the model learns to refine the noisy lane anchors in a progressive way to obtain the target lanes. Secondly, we propose a hybrid decoding strategy to address the poor feature representation of the encoder, resulting from the noisy lane anchors. Specifically, we design a hybrid diffusion decoder to combine global-level and local-level decoders for high-quality lane anchors. Then, to improve the feature representation of the encoder, we employ an auxiliary head in the training stage to adopt the learnable lane anchors for enriching the supervision on the encoder. Experimental results on four benchmarks, Carlane, Tusimple, CULane, and LLAMAS, show that DiffusionLane possesses a strong generalization ability and promising detection performance compared to the previous state-of-the-art methods. For example, DiffusionLane with ResNet18 surpasses the existing methods by at least 1\% accuracy on the domain adaptation dataset Carlane. Besides, DiffusionLane with MobileNetV4 gets 81.32\% F1 score on CULane, 96.89\% accuracy on Tusimple with ResNet34, and 97.59\% F1 score on LLAMAS with ResNet101. Code will be available at https://github.com/zkyntu/UnLanedet.