Adaptive Unfolding Total Variation Network for Low-Light Image Enhancement

TL;DR

This paper introduces UTVNet, an adaptive neural network that estimates noise levels in sRGB low-light images to enhance visibility and suppress noise effectively, outperforming existing methods.

Contribution

The paper proposes a novel adaptive unfolding total variation network that learns noise levels directly from real low-light images in sRGB space, improving detail recovery and noise suppression.

Findings

UTVNet outperforms state-of-the-art methods on real low-light images.

The model effectively estimates noise levels in sRGB space.

Enhanced detail preservation and noise suppression in low-light scenes.

Abstract

Real-world low-light images suffer from two main degradations, namely, inevitable noise and poor visibility. Since the noise exhibits different levels, its estimation has been implemented in recent works when enhancing low-light images from raw Bayer space. When it comes to sRGB color space, the noise estimation becomes more complicated due to the effect of the image processing pipeline. Nevertheless, most existing enhancing algorithms in sRGB space only focus on the low visibility problem or suppress the noise under a hypothetical noise level, leading them impractical due to the lack of robustness. To address this issue,we propose an adaptive unfolding total variation network (UTVNet), which approximates the noise level from the real sRGB low-light image by learning the balancing parameter in the model-based denoising method with total variation regularization. Meanwhile, we learn the noise level map by unrolling the corresponding minimization process for providing the inferences of smoothness and fidelity constraints. Guided by the noise level map, our UTVNet can recover finer details and is more capable to suppress noise in real captured low-light scenes. Extensive experiments on real-world low-light images clearly demonstrate the superior performance of UTVNet over state-of-the-art methods.