Super-resolving Real-world Image Illumination Enhancement: A New Dataset and A Conditional Diffusion Model

TL;DR

This paper introduces a new dataset and a conditional diffusion model to enhance super-resolution in real-world low-light images, addressing the limitations of existing methods in preserving details under complex noise conditions.

Contribution

It presents the SRRIIE dataset capturing real low-light conditions and a novel diffusion model with a time-melding condition for improved super-resolution performance.

Findings

Existing methods struggle with noise and structure preservation in low-light images.

The proposed diffusion model outperforms traditional methods on real-world benchmarks.

The SRRIIE dataset enables better training and evaluation of super-resolution algorithms.

Abstract

Most existing super-resolution methods and datasets have been developed to improve the image quality in well-lighted conditions. However, these methods do not work well in real-world low-light conditions as the images captured in such conditions lose most important information and contain significant unknown noises. To solve this problem, we propose a SRRIIE dataset with an efficient conditional diffusion probabilistic models-based method. The proposed dataset contains 4800 paired low-high quality images. To ensure that the dataset are able to model the real-world image degradation in low-illumination environments, we capture images using an ILDC camera and an optical zoom lens with exposure levels ranging from -6 EV to 0 EV and ISO levels ranging from 50 to 12800. We comprehensively evaluate with various reconstruction and perceptual metrics and demonstrate the practicabilities of the SRRIIE dataset for deep learning-based methods. We show that most existing methods are less effective in preserving the structures and sharpness of restored images from complicated noises. To overcome this problem, we revise the condition for Raw sensor data and propose a novel time-melding condition for diffusion probabilistic model. Comprehensive quantitative and qualitative experimental results on the real-world benchmark datasets demonstrate the feasibility and effectivenesses of the proposed conditional diffusion probabilistic model on Raw sensor data. Code and dataset will be available at https://github.com/Yaofang-Liu/Super-Resolving