SurroundNet: Towards effective low-light image enhancement

Although Convolution Neural Networks (CNNs) have made substantial progress in the low-light image en-hancement task, one critical problem of CNNs is the paradox of model complexity and performance. This paper presents a novel SurroundNet that only involves less than 150 K parameters (about 80-98 percent size reduction compared to SOTAs) and achieves very competitive performance. The proposed network comprises several Adaptive Retinex Blocks (ARBlock), which can be viewed as a novel extension of Single Scale Retinex in feature space. The core of our ARBlock is an efficient illumination estimation function called Adaptive Surround Function (ASF). It can be regarded as a general form of surround functions and be implemented by convolution layers. In addition, we also introduce a Low-Exposure Denoiser (LED) to smooth the low-light image before the enhancement. We evaluate the proposed method on two real -world low-light datasets. Experimental results demonstrate the superiority of our submitted Surround -Net in both performance and network parameters against State-of-the-Art low-light image enhancement methods. The code is available at https://github.com/ouc- ocean- group/SurroundNet .(c) 2023 Elsevier Ltd. All rights reserved.

Automated summary

This paper presents a novel SurroundNet approach that achieves very competitive performance with less than 150K parameters, which is a significant reduction in size compared to other methods. The proposed method, consisting of Adaptive Retinex Blocks and an illumination estimation function called Adaptive Surround Function, is evaluated on two real-world low-light datasets and outperforms existing methods in both performance and network parameters.