Dropout the High-rate Downsampling: A Novel Design Paradigm for UHD Image Restoration

TL;DR

This paper introduces D2Net, a novel method for UHD image restoration that enables direct full-resolution processing without downsampling or patching, leveraging frequency domain features and multi-scale convolutions.

Contribution

D2Net is the first approach to perform full-resolution UHD image restoration without high-rate downsampling or patch division, improving accuracy and reducing artifacts.

Findings

Outperforms state-of-the-art methods in UHD image restoration tasks

Achieves better quantitative and qualitative results

Handles multiple tasks like dehazing, deblurring, and low-light enhancement

Abstract

With the popularization of high-end mobile devices, Ultra-high-definition (UHD) images have become ubiquitous in our lives. The restoration of UHD images is a highly challenging problem due to the exaggerated pixel count, which often leads to memory overflow during processing. Existing methods either downsample UHD images at a high rate before processing or split them into multiple patches for separate processing. However, high-rate downsampling leads to significant information loss, while patch-based approaches inevitably introduce boundary artifacts. In this paper, we propose a novel design paradigm to solve the UHD image restoration problem, called D2Net. D2Net enables direct full-resolution inference on UHD images without the need for high-rate downsampling or dividing the images into several patches. Specifically, we ingeniously utilize the characteristics of the frequency domain to establish long-range dependencies of features. Taking into account the richer local patterns in UHD images, we also design a multi-scale convolutional group to capture local features. Additionally, during the decoding stage, we dynamically incorporate features from the encoding stage to reduce the flow of irrelevant information. Extensive experiments on three UHD image restoration tasks, including low-light image enhancement, image dehazing, and image deblurring, show that our model achieves better quantitative and qualitative results than state-of-the-art methods.