Deep Quantigraphic Image Enhancement via Comparametric Equations
This work addresses a specific bottleneck in image enhancement for computer vision applications, offering an incremental improvement over existing methods.
The paper tackles the constraint in illumination estimation-centric deep image enhancement methods by proposing a novel trainable module based on comparametric equations, which improves flexibility and allows for fully unsupervised learning while maintaining efficiency.
Most recent methods of deep image enhancement can be generally classified into two types: decompose-and-enhance and 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.