A Two-Stage Exposure Controllable Network for Image Enhancement With Low-Light Degradation
- 6 October 2025
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 74 (00189456) , 1-15
Abstract
Controllable low-light enhancement is beneficial to both image aesthetics and high-level vision tasks. Existing methods fail to generate smooth brightness transitions with low cost. In this paper, 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 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.Keywords
Funding Information
- National Natural Science Foundation of China (62572188, 62272164, 62306113)
- Aeronautical Science Foundation of China (202400550S7003, 202400550S7004)
This publication has 72 references indexed in Scilit:
- ULE-Net: Unsupervised Low-Light Enhancement without Paired DataJournal of Signal Processing Systems, 2024
- LightenDiffusion: Unsupervised Low-Light Image Enhancement with Latent-Retinex Diffusion Models2024
- Depicting Beyond Scores: Advancing Image Quality Assessment Through Multi-modal Language Models2024
- Fast Context-Based Low-Light Image Enhancement via Neural Implicit Representations2024
- Denoising diffusion post-processing for low-light image enhancementPattern Recognition, 2024
- PIE: Physics-Inspired Low-Light EnhancementInternational Journal of Computer Vision, 2024
- Global-and-local aware network for low-light image enhancementEngineering Applications of Artificial Intelligence, 2023
- Instance Segmentation in the DarkInternational Journal of Computer Vision, 2023
- R2RNet: Low-light image enhancement via Real-low to Real-normal NetworkJournal of Visual Communication and Image Representation, 2022
- Blind/Referenceless Image Spatial Quality Evaluator2011