High-Resolution Driving Scene Synthesis Using Stacked Conditional Gans and Spectral Normalization

Shaobo Lin, Long Chen, Qin Zou, Wei Tian

Abstract: Large-scale dataset plays a key role in the driving scene understanding for deep learning based-autonomous driving tasks. Due to the fact that the annotation for a large number of images is extremely labor-intensive and time-consuming, many researchers turn to using image-synthesis techniques for automatic construction of training data. However, traditional methods often have difficulties in producing high-definition driving scene images. To tackle this problem, in this paper, we propose a novel deep model - hdCGAN - for high-definition image-to-image translation. The hdCGAN is built on a conditional GAN in combination with a spectral normalization. Moreover, we improve the hdCGAN by using a stacked network architecture and the enhanced model is called stack-hdCGAN. With the guidance of multi-scale discriminators and the constraint of spectral normalization in the training procedure, the learned models can generate high-resolution and high-quality driving scene images from corresponding semantic segmentation maps. Quantitative and qualitative evaluations on the Cityscapes dataset demonstrate the effectiveness of the proposed models.