Abstract
Image rain removal aims to separate the background image from the rainy image. During the past three years, the image rain removal with deep convolutional neural networks has achieved impressive performance. However, how to reach tradeoff between high de-raining performance and low model parameters is still a challenge. To address the issue, the paper is devoted to exploring a novel method based on wavelet deep recursive pyramid convolution residual network (WDRPRN), in which discrete wavelet transform is embedded to decompose the rainy image in different frequency domains, and the deep recursive pyramid convolution residual network (DRPRN) can well predict the residual coefficients between rainy image and clean image. In addition, compared with other neural networks, the DRPRN adopts recursive model that can cost fewer parameters. Plentiful of experiments on synthetic and real-world datasets show that the proposed method is significantly superior to the recent state-of-the-art algorithms.
Highlights
Image rain removal is a fundamental task in low-level computer vision
We propose a light wavelet deep recursive pyramid convolution residual network (WDRPRN), which only owns about 68k parameters, and the de-raining performance metrics overtake some advanced methods
2) EVALUATION ON REAL-WORLD RAINY IMAGES To test the WDRPRN de-raining performance in real-world rainy images, our network is trained on Rain800, and tests the actual de-raining result on Rain50 real-world dataset
Summary
Image rain removal is a fundamental task in low-level computer vision. The bad rainy images with rain streaks and fog artifacts degrade human visual perception, and reduce the accuracy of many high-level computer vision tasks, such as pedestrian detection [1], visual tracking [2], scene analysis [3] and saliency detection [4]. It is a vital research work to remove the rain streaks and recover the details of the background image. This paper is committed to the study of single image rain removal. The light rainy image is mainly composed of slender rain streaks and detail background image. For heavy rainy image, this may be caused by rain accumulation [5], which can form a veil on the background image. The rain model can be expressed as follows: O=B+S (1)
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
