Exploring Overcomplete Representations for Single Image Deraining using CNNs

10/20/2020
by   Rajeev Yasarla, et al.
5

Removal of rain streaks from a single image is an extremely challenging problem since the rainy images often contain rain streaks of different size, shape, direction and density. Most recent methods for deraining use a deep network following a generic "encoder-decoder" architecture which captures low-level features across the initial layers and high-level features in the deeper layers. For the task of deraining, the rain streaks which are to be removed are relatively small and focusing much on global features is not an efficient way to solve the problem. To this end, we propose using an overcomplete convolutional network architecture which gives special attention in learning local structures by restraining the receptive field of filters. We combine it with U-Net so that it does not lose out on the global structures as well while focusing more on low-level features, to compute the derained image. The proposed network called, Over-and-Under Complete Deraining Network (OUCD), consists of two branches: overcomplete branch which is confined to small receptive field size in order to focus on the local structures and an undercomplete branch that has larger receptive fields to primarily focus on global structures. Extensive experiments on synthetic and real datasets demonstrate that the proposed method achieves significant improvements over the recent state-of-the-art methods.

READ FULL TEXT

page 1

page 2

page 4

page 7

page 8

page 9

research
06/16/2021

Over-and-Under Complete Convolutional RNN for MRI Reconstruction

Reconstructing magnetic resonance (MR) images from undersampled data is ...
research
05/31/2022

SAR Despeckling Using Overcomplete Convolutional Networks

Synthetic Aperture Radar (SAR) despeckling is an important problem in re...
research
10/04/2020

KiU-Net: Overcomplete Convolutional Architectures for Biomedical Image and Volumetric Segmentation

Most methods for medical image segmentation use U-Net or its variants as...
research
08/04/2018

Non-locally Enhanced Encoder-Decoder Network for Single Image De-raining

Single image rain streaks removal has recently witnessed substantial pro...
research
09/10/2019

Confidence Measure Guided Single Image De-raining

Single image de-raining is an extremely challenging problem since the ra...
research
09/20/2021

R2D: Learning Shadow Removal to Enhance Fine-Context Shadow Detection

Current shadow detection methods perform poorly when detecting shadow re...
research
04/12/2023

SGL: Structure Guidance Learning for Camera Localization

Camera localization is a classical computer vision task that serves vari...

Please sign up or login with your details

Forgot password? Click here to reset