Research on low-light image enhancement based on MER-Retinex algorithm

Abstract

To solve blurring and poor visual effects after enhancement of low-light images by conventional low-light algorithms, this paper proposes a MER-Retinex (Multiscale Expansion Reconstruction Retinex) algorithm that integrates attention mechanism and multi-scale expansion pyramid reconstruction. It includes two parts: decomposition and enhancement module. In the decomposition module, two U-shaped networks are used to decompose the image into reflectance and illumination, then, use multi-layer convolution to expand the field of perception and improve the ability to decompose the image to obtain reflectance and illumination. In the enhancement module, a U-shaped network is used to fuse multi-scale expansion pyramids with a multi-attention mechanism to enrich image information, increase image brightness, and fuse the processed global information with local information to enhance the recovered image details. In the enhanced reconstruction section super-resolution techniques are used to enhance and denoise image feature details. Experimental analysis of the MER-Retinex algorithm was carried out on the LOL dataset. The PSNR of the algorithm in this paper was 25.26 and the NIQE was 3.43. The algorithm in this paper can effectively solve the problems of blurred images and poor visual effects, and has improved in both subjective perception and objective evaluation indexes.

ZRRD-MBNet：Zero-Reference RETINEX Decomposition-Based Multi-Branch Network for Low-Light Image Enhancement

“…Subsequently, the mapping map is adjusted pixel by pixel to obtain the final result. Zhou et al [7] combined the attention mechanism with multi-scale extended pyramid reconstruction to enhance low-light images. The introduction of the attention mechanism facilitated the restoration of image details.…”

A Low-Light Image Enhancement Algorithm Incorporating Cross-Mixed Attention and Receptive Field Expansion Mechanism

“…So, the low-light image enhancement have received tremendous boost owing to many potential applications, such as nighttime aerial photography [1] [2], self-driving cars at night [3] [4], etc. Low-light image enhancement algorithms are mainly classified into three categories: distribution mapping-based methods [5] [6], model optimization-based methods [7] [8], and deep learning-based methods [9] [10] [11]. The curve transformations, histogram equalization, and other means were used to adjust information of low-light images in the distribution mapping-based methods, however, in these methods, there will be drawbacks such as overexposure and underexposure.…”