文献类型：期刊文献

英文题名：A Two-Stage Exposure Controllable Network for Image Enhancement With Low-Light Degradation

作者：Liang, Lei[1];Chen, Zhihua[1];Dai, Lei[1];Chen, Ruoxin[2];Zhang, Yunyi[1];He, Xufeng[1]

机构：[1]East China Univ Sci & Technol, Dept Comp Sci & Engn, Shanghai 200237, Peoples R China;[2]Tencent Youtu Lab, Shanghai 200232, Peoples R China

年份：2025

卷号：74

外文期刊名：IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT

收录：;EI(收录号：20254219346945);WOS:【SCI-EXPANDED(收录号:WOS:001608974400024)】；

基金：This work was supported in part by the National Natural Science Foundation of China under Grant 62572188, Grant 62272164, and Grant 62306113; and in part by the Aeronautical Science Foundation of China under Grant 202400550S7003 and Grant 202400550S7004.

语种：英文

外文关键词：Exposure reference; low-light image; offline ffl ine exposure control; offline ffl ine exposure control; progressive enhancement; vision-based mea-surement system (VMS); vision-based mea-surement system (VMS)

摘要：Controllable low-light enhancement is beneficial to both image aesthetics and high-level vision tasks. Existing methods fail to generate smooth brightness transitions at low cost. In this article, we propose an unsupervised two-stage exposure controllable network (TSECN) featuring low-cost and natural brightness customization. Conditioning on a color-correlation-based exposure reference map (CERM), an offline naturalness-preserving exposure controller (ONEC) is implemented by modulating a latent scene illumination representation, which is predicted via a two-stage progressive enhancement pipeline (TPE). Specifically, the first stage performs unsupervised low-light denoising and improves visibility with deep gamma correction. The latter handles fine-grained quality refinement and representation learning. Extensive evaluations demonstrate the superior performance of our method across eight real-world datasets. On three paired datasets, TSECN outperforms advanced methods by an average peak signal-to-noise ratio (PSNR) improvement of 2.29 dB. Experiments on two high-level vision tasks also validate its value in application-oriented scenarios. The code will be available at https://github.com/cherrysherryplus/TSECN