Restormer-Plus for Real World Image Deraining: One State-of-the-Art Solution to the GT-RAIN Challenge (CVPR 2023 UG^2+ Track 3)

by   Chaochao Zheng, et al.

This technical report presents our Restormer-Plus approach, which was submitted to the GT-RAIN Challenge (CVPR 2023 UG^2+ Track 3). Details regarding the challenge are available at Our Restormer-Plus outperformed all other submitted solutions in terms of peak signal-to-noise ratio (PSNR). It consists mainly of four modules: the single image de-raining module, the median filtering module, the weighted averaging module, and the post-processing module. We named the single-image de-raining module Restormer-X, which is built on Restormer and performed on each rainy image. The median filtering module is employed as a median operator for the 300 rainy images associated with each scene. The weighted averaging module combines the median filtering results with that of Restormer-X to alleviate overfitting if we only use Restormer-X. Finally, the post-processing module is used to improve the brightness restoration. Together, these modules render Restormer-Plus to be one state-of-the-art solution to the GT-RAIN Challenge. Our code is available at


page 2

page 3


A Two-Stage Real Image Deraining Method for GT-RAIN Challenge CVPR 2023 Workshop UG^2+ Track 3

In this technical report, we briefly introduce the solution of our team ...

NTIRE 2020 Challenge on Image Demoireing: Methods and Results

This paper reviews the Challenge on Image Demoireing that was part of th...

Filtering In Neural Implicit Functions

Neural implicit functions are highly effective for representing many kin...

1st Solution Places for CVPR 2023 UG^2+ Challenge Track 2.2-Coded Target Restoration through Atmospheric Turbulence

In this technical report, we briefly introduce the solution of our team ...

Convolutional Neural Network with Median Layers for Denoising Salt-and-Pepper Contaminations

We propose a deep fully convolutional neural network with a new type of ...

GridDehazeNet: Attention-Based Multi-Scale Network for Image Dehazing

We propose an end-to-end trainable Convolutional Neural Network (CNN), n...

Nest-DGIL: Nesterov-optimized Deep Geometric Incremental Learning for CS Image Reconstruction

Proximal gradient-based optimization is one of the most common strategie...

Please sign up or login with your details

Forgot password? Click here to reset