Neural Neighbor Style Transfer
This addresses the problem of generating high-quality stylized images for artistic applications, but it appears incremental as it builds on prior work with design improvements.
The paper tackles artistic style transfer by proposing Neural Neighbor Style Transfer (NNST), a pipeline that achieves state-of-the-art quality and generalization with competitive efficiency.
We propose Neural Neighbor Style Transfer (NNST), a pipeline that offers state-of-the-art quality, generalization, and competitive efficiency for artistic style transfer. Our approach is based on explicitly replacing neural features extracted from the content input (to be stylized) with those from a style exemplar, then synthesizing the final output based on these rearranged features. While the spirit of our approach is similar to prior work, we show that our design decisions dramatically improve the final visual quality.