Automatic Model-Based Dataset Generation for High-Level Vision Tasks of Autonomous Driving in Haze Weather

Abstract

Improving the performance of high-level computer vision tasks in adverse weather (e.g., haze) is highly critical for autonomous driving safety. However, collecting and annotating training sets for various high-level tasks in haze weather is expensive and time-consuming. To address this issue, we propose a novel haze generation model called HazeGEN by coupling the variational autoencoder (VAE) and the generative adversarial network (GAN) to automatically generate annotated datasets. The proposed HazeGEN leverages a shared latent space assumption based on an optimized encoder-decoder architecture, which guarantees high fidelity in the cross-domain image translations. To ensure that the generated image can truly facilitate high-level vision task performance, a semi-supervised learning strategy is developed for HazeGEN to efficiently learn the useful knowledge from both the real-world images (with unsupervised losses) and the synthetic images generated following the atmosphere scattering model (with supervised losses). Extensive experiments and ablation studies demonstrate that training the model with our generated haze dataset greatly improves accuracy in high-level tasks such as semantic segmentation and object detection. Furthermore, one important but under-exploited issue is investigated to find out whether the developed dataset can be a good substitute for the real ones. Results show that the generated dataset has the most similar performance to the real-world collected haze dataset on multiple challenging industrial scenarios compared with prior works.