ForkGAN: Seeing into the Rainy Night
Ziqiang Zheng, Yang Wu, Xinran Han, Jianbo Shi
Abstract
We present a ForkGAN for task-agnostic image translation that can boost multiple vision tasks in adverse weather conditions. Three tasks of image localization/retrieval, semantic image segmentation, and object detection are evaluated. The key challenge is achieving high-quality image translation without any explicit supervision, or task awareness. Our innovation is a fork-shape generator with one encoder and two decoders that disentangles the domain-specific and domain-invariant information. We force the cyclic translation between the weather conditions to go through a common encoding space, and make sure the encoding features reveal no information about the domains. Experimental results show our algorithm produces state-of-the-art image synthesis results and boost three vision tasks' performances in adverse weathers."
BibTeX
@inproceedings{eccv2020_forkganseeingint,
title = {ForkGAN: Seeing into the Rainy Night},
author = {Ziqiang Zheng and Yang Wu and Xinran Han and Jianbo Shi},
booktitle = {ECCV 2020},
year = {2020}
}