Style transfer is the task of changing the style of an image in one domain to the style of an image in another domain.
( Image credit: A Neural Algorithm of Artistic Style )
We propose an approach to domain adaptation for semantic segmentation that is both practical and highly accurate.
Ranked #1 on Domain Adaptation on SYNTHIA-to-Cityscapes
Inspired by the common painting process of drawing a draft and revising the details, we introduce a novel feed-forward method named Laplacian Pyramid Network (LapStyle).
Many of the existing style transfer benchmarks primarily focus on individual high-level semantic changes (e. g. positive to negative), which enable controllability at a high level but do not offer fine-grained control involving sentence structure, emphasis, and content of the sentence.
Leveraging the learned structure of the latent space, we find moving in this direction corrects many image artifacts and brings the image into greater realism.
We take the first step towards multilingual style transfer by creating and releasing XFORMAL, a benchmark of multiple formal reformulations of informal text in Brazilian Portuguese, French, and Italian.
However, existing works overlooked the latter components and confined makeup transfer to color manipulation, focusing only on light makeup styles.
Ranked #1 on Facial Makeup Transfer on CPM-Synt-2