Arbitrary Style Transfer With Style-Attentional Networks

By Dae Young Park, Kwang Hee Lee. 2018

495 citations recorded by the source corpus.

Arbitrary style transfer aims to synthesize a content image with the style of an image to create a third image that has never been seen before. Recent arbitrary style transfer algorithms find it challenging to balance the content structure and the style patterns. Moreover, simultaneously maintaining the global and local style patterns is difficult due to the patch-based mechanism. In this paper, we introduce a novel style-attentional network (SANet) that efficiently and flexibly integrates the local style patterns according to the semantic spatial distribution of the content image. A new identity loss function and multi-level feature embeddings enable our SANet and decoder to preserve the content structure as much as possible while enriching the style patterns. Experimental results demonstrate that our algorithm synthesizes stylized images in real-time that are higher in quality than those produced by the state-of-the-art algorithms.

Subfields: Computer Vision and Pattern Recognition, Generative Models

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

In Generative Models

Citations in the corpus

A Disentangling Invertible Interpretation Network for Explaining Latent Representations (2020, methodology): “We then utilize a style transfer algorithm [40] to transform each x from the training set into two new images: x a and x b which are stylized with y a and y b , respectively.”
StyleFormer: Real-time Arbitrary Style Transfer via Parametric Style Composition (2021, methodology): “When compared with the prior optimization-based [1, 3] and feed-forward based approaches [18, 17, 25, 19, 23, 35], our method achieves the SOTA stylization re-sults in terms of both visual quality and efficiency.”
AdaAttN: Revisit Attention Mechanism in Arbitrary Neural Style Transfer (2021, methodology): “By taking local style patterns into consideration, SANet [28] calculates attention map from the style and content feature maps and then modulates the style feature with the attention map to fuse the attention output into the content feature.”
Style Injection in Diffusion: A Training-Free Approach for Adapting Large-Scale Diffusion Models for Style Transfer (2023, unknown): “Neural style transfer [11, 24–26, 29, 31, 43, 44, 52] is an example-guided image generation task that transfers the style of one image onto another while retaining the content of the original.”
StyTr2: Image Style Transfer with Transformers (2021, methodology): “In terms of style loss, SANet [39] and StyTr2 outperform the other methods.”
Rethinking and Improving the Robustness of Image Style Transfer (2021, background): “A consistent observation from this work [43, 24, 30, 23, 25, 19, 9, 2, 8] is that the correlation between the activations of a pre-trained VGG [33] network has remarkable ability to capture the visual style of an image.”