We are pleased to announce that our paper “Deep quantigraphic image enhancement via comparametric equations” has been accepted to ICASSP2023.
Xiaomeng Wu, Yongqing Sun, Akisato Kimura, “Deep quantigraphic image enhancement via comparametric equations,” IEEE International Conference on Acoustic, Speech and Signal Processing (ICASSP), 2023. (oral)
Most recent methods of deep image enhancement can be generally classified into two types:
- Decompose and enhance
- Illumination estimation centric
The former is usually less efficient, and the latter is constrained by a strong assumption regarding image reflectance as the desired enhancement result.
To alleviate this constraint while retaining high efficiency, we propose a novel trainable module that diversifies the conversion from the low-light image and illumination map to the enhanced image. It formulates image enhancement as a comparametric equation parameterized by a camera response function and an exposure compensation ratio.
By incorporating this module in an illumination estimation-centric DNN, our method improves the flexibility of deep image enhancement, limits the computational burden to illumination estimation, and allows for fully unsupervised learning adaptable to the diverse demands of different tasks.
A pre-print version can be found at https://arxiv.org/abs/2304.02285, and the source code is also available at https://github.com/nttcslab/cone .