SIMI: Self-information Mining Network for Low-light Image Enhancement
For computer vision practitioners, this work offers an efficient unsupervised method for low-light image enhancement that outperforms existing approaches without requiring external data.
The paper proposes SIMI, an unsupervised low-light image enhancement network that uses bit-plane decomposition to mine intrinsic information, achieving state-of-the-art performance on standard benchmarks with faster convergence and lower computational cost.
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.