LanePainter: Lane marks Enhancement via Generative Adversarial Network

Brief Project Description: Lane detection is one of the popular research fields in computer vision and autonomous vehicles. However, the performance of lane mark detection algorithms under low-quality lane marking environments is rarely studied. In this paper, we study this problem and propose LanePainter, a GAN-based model for simultaneously classifying and enhancing the lane marks. In this work, we demonstrate that our model can successfully detect low-quality lane marks. And, the enhanced lane marks can improve the performance of existing lane detection algorithms on low-quality lane marks.

Poster: 

Fact Sheet     Video     Other     Q&A

Presenter: Xiaohan Zhang, UVM