Cardiff University | Prifysgol Caerdydd ORCA
Online Research @ Cardiff 
WelshClear Cookie - decide language by browser settings

A decomposed dual-cross generative adversarial network for image rain removal

Jin, Xin, Chen, Zhibo, Lin, Jianxin, Chen, Jiale, Zhou, Wei and Shan, Chaowei 2018. A decomposed dual-cross generative adversarial network for image rain removal. Presented at: British Machine Vision Conference 2018, Newcastle, UK, 3-6 September 2018.

Full text not available from this repository.


Rain removal is important for many computer vision applications, such as surveillance, autonomous car, etc. Traditionally, rain removal is regarded as a signal removal problem which usually causes over-smoothing by removing texture details in non-rain background regions. This paper considers the issue of rain removal from a completely different perspective, to treat rain removal as a signal decomposition problem. Specifically, we decompose the rain image into two components, namely non-rain background image and rain streaks image. Then, we introduce an adversarial training mechanism to synthesize non-rain background image and rain streaks image in a Dual-Cross manner, which makes the two adversarial branches interact with each other, archiving a win-win result ultimately. The proposed Decomposed Dual-Cross Generative Adversarial Network (DDC-GAN) shows significantly performance improvement compared with stateof-the-art methods on both synthetic and real-world images in terms of qualitative and quantitative measures (over 3dB gains in PSNR).

Item Type: Conference or Workshop Item (Paper)
Date Type: Completion
Status: Unpublished
Schools: Computer Science & Informatics
Last Modified: 24 Aug 2023 15:15

Actions (repository staff only)

Edit Item Edit Item