[ECCV 2020 Oral Long Talk] ForkGAN: Seeing into the Rainy Night

ECCV 2020

[ECCV 2020 Oral Long Talk] ForkGAN: Seeing into the Rainy Night

Aug 18, 2020
|
174 views
Details
Long talk for ECCV 2020 oral paper: Title: ForkGAN: Seeing into the Rainy Night Authors: Ziqiang Zheng, Yang Wu, Xinran Han, and 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. Code: https://github.com/zhengziqiang/ForkGAN

Comments
loading...