High-Frequency aware Perceptual Image Enhancement

TL;DR

This paper presents a deep neural network designed for multi-scale image enhancement that effectively captures high-frequency details, outperforming existing methods in denoising, deblurring, and super-resolution tasks.

Contribution

The paper introduces a novel multi-scale neural network with model-agnostic high-frequency extraction techniques for improved image enhancement.

Findings

Achieves state-of-the-art results on multiple datasets

Overcomes over-smoothing in PSNR-oriented methods

Generates more natural high-resolution images with adversarial training

Abstract

In this paper, we introduce a novel deep neural network suitable for multi-scale analysis and propose efficient model-agnostic methods that help the network extract information from high-frequency domains to reconstruct clearer images. Our model can be applied to multi-scale image enhancement problems including denoising, deblurring and single image super-resolution. Experiments on SIDD, Flickr2K, DIV2K, and REDS datasets show that our method achieves state-of-the-art performance on each task. Furthermore, we show that our model can overcome the over-smoothing problem commonly observed in existing PSNR-oriented methods and generate more natural high-resolution images by applying adversarial training.