Flexible Example-based Image Enhancement with Task Adaptive Global Feature Self-Guided Network
This work addresses image enhancement for computer vision applications, offering a flexible and efficient solution, though it appears incremental as it builds on existing SGN architecture with modifications.
The paper tackles the problem of multitask image enhancement by proposing a network that learns one-to-many and many-to-one mappings, outperforming state-of-the-art methods in single tasks with fewer parameters and achieving higher performance in multitask settings through shared representations.
We propose the first practical multitask image enhancement network, that is able to learn one-to-many and many-to-one image mappings. We show that our model outperforms the current state of the art in learning a single enhancement mapping, while having significantly fewer parameters than its competitors. Furthermore, the model achieves even higher performance on learning multiple mappings simultaneously, by taking advantage of shared representations. Our network is based on the recently proposed SGN architecture, with modifications targeted at incorporating global features and style adaption. Finally, we present an unpaired learning method for multitask image enhancement, that is based on generative adversarial networks (GANs).