DeepAI AI Chat
Log In Sign Up

Direction-aware Feature-level Frequency Decomposition for Single Image Deraining

06/15/2021
by   Sen Deng, et al.
0

We present a novel direction-aware feature-level frequency decomposition network for single image deraining. Compared with existing solutions, the proposed network has three compelling characteristics. First, unlike previous algorithms, we propose to perform frequency decomposition at feature-level instead of image-level, allowing both low-frequency maps containing structures and high-frequency maps containing details to be continuously refined during the training procedure. Second, we further establish communication channels between low-frequency maps and high-frequency maps to interactively capture structures from high-frequency maps and add them back to low-frequency maps and, simultaneously, extract details from low-frequency maps and send them back to high-frequency maps, thereby removing rain streaks while preserving more delicate features in the input image. Third, different from existing algorithms using convolutional filters consistent in all directions, we propose a direction-aware filter to capture the direction of rain streaks in order to more effectively and thoroughly purge the input images of rain streaks. We extensively evaluate the proposed approach in three representative datasets and experimental results corroborate our approach consistently outperforms state-of-the-art deraining algorithms.

READ FULL TEXT

page 2

page 3

page 5

03/21/2023

A High-Frequency Focused Network for Lightweight Single Image Super-Resolution

Lightweight neural networks for single-image super-resolution (SISR) tas...
05/29/2019

Stabilizing GANs with Octave Convolutions

In this preliminary report, we present a simple but very effective techn...
12/20/2017

Learning a Wavelet-like Auto-Encoder to Accelerate Deep Neural Networks

Accelerating deep neural networks (DNNs) has been attracting increasing ...
09/16/2022

Single Image Deraining via Rain-Steaks Aware Deep Convolutional Neural Network

It is challenging to remove rain-steaks from a single rainy image becaus...
10/11/2010

Hierarchical Multiclass Decompositions with Application to Authorship Determination

This paper is mainly concerned with the question of how to decompose mul...
04/10/2023

FreConv: Frequency Branch-and-Integration Convolutional Networks

Recent researches indicate that utilizing the frequency information of i...
08/12/2020

Towards Geometry Guided Neural Relighting with Flash Photography

Previous image based relighting methods require capturing multiple image...