SIMI: Self-information Mining Network for Low-light Image Enhancement

TL;DR

The paper introduces SIMI, an unsupervised network that enhances low-light images by decomposing them into components to extract intrinsic information, leading to improved performance and efficiency.

Contribution

It presents a novel unsupervised framework using bit-plane decomposition for low-light image enhancement, emphasizing intrinsic information mining without external data.

Findings

Achieves state-of-the-art performance on standard benchmarks.

Accelerates convergence and reduces computational overhead.

Effectively extracts intrinsic information from low-light images.

Abstract

Poor lighting conditions significantly impact image quality, posing substantial challenges for image editing and visualization. Many existing enhancement methods aim at proposing complex models while neglecting the intrinsic information contained within low-light images. In this work, we propose the Self-Information Mining (SIMI) network, an innovative unsupervised framework that decomposes low-light images into multiple components based on bit-plane decomposition. Our approach allows mining intrinsic information without relying on external data. This not only accelerates model convergence but also improves performance and reduces computational overhead. The unsupervised nature of our method facilitates real-world applicability. Experiments conducted on standard benchmarks demonstrate that SIMI achieves state-of-the-art performance.