A Semantic-Aware Detail Adaptive Network for Image Enhancement

Low-light images often suffer from varying degrees of visual degradation. Current methods for recovering image texture details fail to rely on the self-adaptive correlation texture direction of the image itself, which leads the network to be unable to address the local texture characteristics of different images. To address this challenge, we propose a semantic-aware detail adaptive network (SDANet) that fully considers the image detail information. The network divides low-light images into high-frequency and low-frequency parts. Learning different forms of noise through a novel total variation regularization module with adaptive weights ensures that the final high-frequency part adequately integrates the texture information of the image. Simultaneously, a detail-adaptive module is incorporated to restore finer details in the resulting image. SDANet not only effectively suppresses noise in real low-light images while considering texture details but also effectively addresses the degradation of visible information, and it performs better than other state-of-the-art methods. The code is available at https://github.com/cheer79/SDANet.

I. Introduction

Low-light images often have low visibility that does not satisfy the human eye’s perception requirements. Among the tasks in the field of computer vision, low-light image enhancement (LLIE) is a fundamental and important branch that aims to improve the visibility of an image and is a technique for reconstructing and enhancing the illumination of an image under low-light conditions [1]. This technique not only helps humans better observe and understand visual scenes but also helps downstream tasks better capture rich visual information in unpredictable and complex scenarios, such as facial recognition [2], image segmentation [3], object detection [4], [5] infrared and visible image fusion [6], [7] and 3D reconstruction [8]. However, as photos captured under certain low-light conditions inevitably introduce undesirable noise, artefacts, loss of image details and visual degradation, LLIE becomes extremely challenging.