ExReg: Wide-range Photo Exposure Correction via a Multi-dimensional Regressor with Attention
Authors:
- Tzu-Hao ChiangTCTzu-Hao Chiang
- Hao-Chien HsuehHHHao-Chien Hsueh
- Ching-Chun HsiaoCHChing-Chun Hsiao
- Ching-Chun HuangCHChing-Chun Huang
Preprint
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 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 mainly proposed Encoder-Decoder ANP (Attentive Neural Processes) to regress the final corrected image. The experimental results show that ExReg can generate well-exposed results and outperform the SOTA method by 1.3dB in PSNR for extensive exposure problems. In addition, given the same image but under various exposure for testing, the corrected results are more visually consistent and physically accurate.Keywords
All Related Versions
This publication has 10 references indexed in Scilit:
- EnlightenGAN: Deep Light Enhancement Without Paired SupervisionIEEE Transactions on Image Processing, 2021
- Towards Unsupervised Deep Image Enhancement With Generative Adversarial NetworkIEEE Transactions on Image Processing, 2020
- Kindling the Darkness2019
- HDR image reconstruction from a single exposure using deep CNNsACM Transactions on Graphics, 2017
- Learning a no-reference quality metric for single-image super-resolutionComputer Vision and Image Understanding, 2017
- LIME: Low-Light Image Enhancement via Illumination Map EstimationIEEE Transactions on Image Processing, 2016
- Building machines that learn and think like peopleBehavioral and Brain Sciences, 2016
- Naturalness Preserved Enhancement Algorithm for Non-Uniform Illumination ImagesIEEE Transactions on Image Processing, 2013
- 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