High-Frequency aware Perceptual Image Enhancement
This work addresses image quality enhancement for applications in photography and vision, though it appears incremental as it builds on existing deep learning methods for image processing.
The paper tackles multi-scale image enhancement tasks like denoising, deblurring, and super-resolution by introducing a deep neural network that extracts high-frequency information to reconstruct clearer images, achieving state-of-the-art performance on datasets such as SIDD and DIV2K and overcoming over-smoothing issues with adversarial training.
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.