• Journal of Korea Multimedia Society
• /
• v.22 no.1
• /
• pp.1-9
• /
• 2019

Single image rain removal is a typical inverse problem which decomposes the image into a background scene and a rain streak. Recent works have witnessed a substantial progress on the task due to the development of convolutional neural network (CNN). However, existing CNN-based approaches train the network with synthetically generated training examples. These data tend to make the network bias to the synthetic scenes. In this paper, we present an unsupervised framework for removing rain streaks from real-world rainy images. We focus on the natural phenomena that static rainy scenes capture a common background but different rain streak. From this observation, we train siamese network with the real rain image pairs, which outputs identical backgrounds from the pairs. To train our network, a real rainy dataset is constructed via web-crawling. We show that our unsupervised framework outperforms the recent CNN-based approaches, which are trained by supervised manner. Experimental results demonstrate that the effectiveness of our framework on both synthetic and real-world datasets, showing improved performance over previous approaches.

• Journal of Broadcast Engineering
• /
• v.20 no.1
• /
• pp.153-163
• /
• 2015

This paper proposes a rain detection and removal algorithm that is robust against camera motion in video sequences. In detection part, the proposed algorithm initially detects possible rain streaks by using intensity properties and spatial properties. Then, the rain streak candidates are selected based on Gaussian distribution model. In removal part, a non-rain block matching algorithm is performed between adjacent frames to find similar blocks to the block that has rain pixels. If the similar blocks to the block are obtained, the rain region of the block is reconstructed by non-local means (NLM) filter using the similar neighbors. Experimental results show that the proposed algorithm outperforms the previous works in terms of subjective visual quality of de-rained video sequences.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2020.11a
• /
• pp.113-117
• /
• 2020

Images were taken under various weather such as rain, haze, snow often show low visibility, which can dramatically decrease accuracy of some tasks in computer vision: object detection, segmentation. Besides, previous work to enhance image usually downsample the image to receive consistency features but have not yet good upsample algorithm to recover original size. So, in this research, we jointly implement removal streak in heavy rain image and super resolution using a deep network. We put forth a 2-stage network: a multi-model network followed by a refinement network. The first stage using rain formula in the single image and two operation layers (addition, multiplication) removes rain streak and noise to get clean image in low resolution. The second stage uses refinement network to recover damaged background information as well as upsample, and receive high resolution image. Our method improves visual quality image, gains accuracy in human action recognition task in datasets. Extensive experiments show that our network outperforms the state of the art (SoTA) methods.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2013.06a
• /
• pp.12-13
• /
• 2013

본 논문은 비가 오는 장면을 촬영한 동영상에서 빗줄기를 효과적으로 제거하는 기법을 제안한다. 제안하는 기법에서는 광흐름 검출 기법을 이용하여 인접한 프레임에서 현재 프레임의 픽셀에 대응하는 픽셀을 검출하고, 확률에 따라 해당 프레임의 픽셀 적용 유무를 결정한다. 빗줄기로 검출된 픽셀을 인접한 프레임의 픽셀 값으로 대체함으로써 영상 내 빗줄기를 제거한다. 컴퓨터 모의실험을 통해 제안하는 알고리즘이 동영상에서 효과적으로 빗줄기를 제거할 수 있음을 확인한다.