Interpretable Unsupervised Joint Denoising and Enhancement for Real-World low-light Scenarios
This addresses the challenge of enhancing low-light images in real-world scenarios for applications like photography or surveillance, but it is incremental as it builds on existing unsupervised and retinex-based methods.
The paper tackles the problem of real-world low-light image enhancement, which involves complex degradations like noise and uneven illumination, by proposing an interpretable unsupervised joint denoising and enhancement framework, achieving superior performance in experiments.
Real-world low-light images often suffer from complex degradations such as local overexposure, low brightness, noise, and uneven illumination. Supervised methods tend to overfit to specific scenarios, while unsupervised methods, though better at generalization, struggle to model these degradations due to the lack of reference images. To address this issue, we propose an interpretable, zero-reference joint denoising and low-light enhancement framework tailored for real-world scenarios. Our method derives a training strategy based on paired sub-images with varying illumination and noise levels, grounded in physical imaging principles and retinex theory. Additionally, we leverage the Discrete Cosine Transform (DCT) to perform frequency domain decomposition in the sRGB space, and introduce an implicit-guided hybrid representation strategy that effectively separates intricate compounded degradations. In the backbone network design, we develop retinal decomposition network guided by implicit degradation representation mechanisms. Extensive experiments demonstrate the superiority of our method. Code will be available at https://github.com/huaqlili/unsupervised-light-enhance-ICLR2025.