ExReg: Wide-range Photo Exposure Correction via a Multi-dimensional Regressor with Attention
Open Access
- 19 February 2026
- journal article
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Intelligent Systems and Technology
- Vol. 17 (2) , 1-22
Abstract
Photo exposure correction is widely investigated, but fewer studies focus on correcting under- and over-exposed images simultaneously. Three issues remain open to handle and correct both under- and over-exposed images in a unified way. First, a locally adaptive exposure adjustment may be more flexible instead of learning a global mapping. Second, it is an ill-posed problem to determine the suitable exposure values locally. Third, photos with the same content but different exposures may not reach consistent adjustment results. To this end, we proposed a novel exposure correction network, ExReg, to address the challenges by formulating exposure correction as a multi-dimensional regression process. Given an input image, a compact multi-exposure generation network is introduced to generate images with different exposure conditions for multi-dimensional regression and exposure correction in the next stage. An auxiliary module is designed to predict the region-wise exposure values, guiding the proposed Encoder–Decoder ANP (Attentive Neural Process) to regress the final corrected image. The experimental results show that ExReg can generate well-exposed results and outperform the SOTA method in PSNR for extensive exposure problems. Furthermore, the processing speed, with 0.05 seconds per image on an RTX 3090, is efficient. When tested on the same image under various exposure levels, ExReg also yields results that are visually consistent and physically accurate.Keywords
All Related Versions
Funding Information
- Co-creation Platform of the Industry Academia Innovation School, NYCU (112UA10019)
- National Science and Technology Council, Taiwan (NSTC-114-2218-E-A49-024, NSTC-112-2221-E-A49-089-MY3, NSTC-114-2425-H-A49-001, NSTC-113-2634-F-A49-007, NSTC-112-2221-E-A49-092-MY3)
- MediaTek Inc., Hon Hai Research Institute, and Industrial Technology Research Institute
This publication has 34 references indexed in Scilit:
- UPT-Flow: Multi-scale transformer-guided normalizing flow for low-light image enhancementPattern Recognition, 2024
- Iterative Prompt Learning for Unsupervised Backlit Image Enhancement2023
- Toward Fast, Flexible, and Robust Low-Light Image Enhancement2022
- A No-Reference Evaluation Metric for Low-Light Image Enhancement2021
- Learning Multi-Scale Photo Exposure Correction2021
- Deep Photo Enhancer: Unpaired Learning for Image Enhancement from Photographs with GANs2018
- DSLR-Quality Photos on Mobile Devices with Deep Convolutional Networks2017
- Learning a no-reference quality metric for single-image super-resolutionComputer Vision and Image Understanding, 2017
- Making a “Completely Blind” Image Quality AnalyzerIEEE Signal Processing Letters, 2012
- Adaptive image contrast enhancement using generalizations of histogram equalizationIEEE Transactions on Image Processing, 2000