PercepLIE: A New Path to Perceptual Low-Light Image Enhancement

Cong Wang, Chengjin Yu, Jie Mu, Wei Wang

Abstract: While current CNN-based low-light image enhancement (LIE) approaches have achieved significant progress, they often fail to generate better perceptual quality which requires restoring better details and more natural colors. To address these problems, we set a new path, called PercepLIE, by presenting the VQGAN with Multi-luminance Detail Compensation (MDC) and Global Color Adjustment (GCA). Specifically, observed that latent light features of the low-light images are quite different from those captured in normal light, we utilize VQGAN to explore the latent light representation of normal-light images to help the estimation of the low-light and normal-light mapping. Furthermore, we employ Gamma correction with varying Gamma values on the gradient to create multi-luminance details, forming the basis for our MDC module to facilitate better detail estimation. To optimize the colors of low-light input images, we introduce a simple yet effective GCA module that is based on spatially-varying representation between the estimated normal-light images in this module and low-light inputs. By combining the VQGAN with MDC and GCA within a stage-wise training mechanism, our method generates images with finer details and natural colors and achieves favorable performance on both synthetic and real-world datasets in terms of perceptual quality metrics including NIQE, PI, and LPIPS. The source codes will be made available at \url{https://github.com/supersupercong/PercepLIE}.

Primary Subject Area: [Experience] Multimedia Applications

Secondary Subject Area: [Experience] Multimedia Applications

Relevance To Conference: Images captured in low-light conditions are often captured by outdoor surveillance equipment, which may significantly degrade the performance of some existing computer vision systems and may also result in a pool of visual experience for some multimedia applications.

Submission Number: 3757