On the Diversity of Realistic Image Synthesis
This addresses the issue of low output diversity in image-to-image translation for applications like creative design and data augmentation, though it is an incremental improvement over existing methods.
The paper tackles the problem of limited diversity in image synthesis tasks like colorization and super resolution, where a single input often corresponds to multiple possible outputs, by introducing a diversity loss that maximizes distance between synthesized image pairs and links input noise to semantic segments, resulting in significantly more diverse images without degrading reality.
Many image processing tasks can be formulated as translating images between two image domains, such as colorization, super resolution and conditional image synthesis. In most of these tasks, an input image may correspond to multiple outputs. However, current existing approaches only show very minor diversity of the outputs. In this paper, we present a novel approach to synthesize diverse realistic images corresponding to a semantic layout. We introduce a diversity loss objective, which maximizes the distance between synthesized image pairs and links the input noise to the semantic segments in the synthesized images. Thus, our approach can not only produce diverse images, but also allow users to manipulate the output images by adjusting the noise manually. Experimental results show that images synthesized by our approach are significantly more diverse than that of the current existing works and equipping our diversity loss does not degrade the reality of the base networks.