Efficient Style-Corpus Constrained Learning for Photorealistic Style Transfer

Yingxu Qiao

doi:10.1109/TIP.2021.3058566

Efficient Style-Corpus Constrained Learning for Photorealistic Style Transfer

2021-01-01

18

PRE

AI

DOI：10.1109/TIP.2021.3058566

Original

Original request for help

Save

Abstract

En 中文

Photorealistic style transfer is a challenging task, which demands the stylized image remains real. Existing methods are still suffering from unrealistic artifacts and heavy computational cost. In this paper, we propose a novel Style-Corpus Constrained Learning (SCCL) scheme to address these issues. The style-corpus with the style-specific and style-agnostic characteristics simultaneously is proposed to constrain the stylized image with the style consistency among different samples, which improves photorealism of stylization output. By using adversarial distillation learning strategy, a simple fast-to-execute network is trained to substitute previous complex feature transforms models, which reduces the computational cost significantly. Experiments demonstrate that our method produces rich-detailed photorealistic images, with 13 similar to 50 times faster than the state-of-the-art method (WCT2).

Keywords:

Photorealistic style transfer

generative adversarial network

knowledge distillation

style-corpus

Efficient Style-Corpus Constrained Learning for Photorealistic Style Transfer

Abstract

AI Summary

Journal

Organization