Image-to-image translation aims at translating a particular style of an image to another. The synthesized images can be more photo-realistic and identity-preserving by decomposing the image into content and style in a disentangled manner. While existing models focus on designing specialized network architecture to separate the two components, this paper investigates how to explicitly constrain the content and style statistics of images. We achieve this goal by transforming the input image into high frequency and low frequency information, which correspond to the content and style, respectively. We regulate the frequency distribution from two aspects: a) a spatial level restriction to locally restrict the frequency distribution of images; b) a spectral level regulation to enhance the global consistency among images. On multiple datasets we show that the proposed approach consistently leads to significant improvements on top of various state-of-the-art image translation models.
Yan Yu and co‐workers (DOI: https://doi.org/10.1002/inf2.12176) design and develop the nitrogen‐doped porous carbon nanosheets as the multifunctional host of Se (Se@N‐HCNS). They demonstrate that this structure could absorb polyselenides and facilitate ions transport effectively. In this cover, the fishes preferring to live under the lotus mean the anchoring effect of the Se@N‐HCNS on polyselenides. The buffalo is attracted to the red lanterns, representing the great development potential of K‐Se batteries in the Year of the Ox.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.