Multi-Stage Optimization for Photorealistic Neural Style Transfer

Yang, Richard R.

doi:10.1109/CVPRW.2019.00227

Multi-Stage Optimization for Photorealistic Neural Style Transfer

Richard R. Yang

CVPRW 2019 pp. 1769-1776

doi:10.1109/CVPRW.2019.00227 /cvprw/2019/yang2019cvprw-multistage/

Abstract

This work introduces a new approach toward photorealistic style transfer. When applying current style transfer techniques on real world photographs, the generated results often contain distortions and artifacts that diminish the real-world quality of the photograph. To address these issues, we propose a two-stage optimization process that transfers style globally and regionally and applies a sharpening filter after each step. As evaluated by a user study, our method is qualitatively comparable to existing state-of-the-art methods, but successfully handles previous failure cases. Our method also quantitatively outperform previous methods as evaluated by natural scene statistic metrics.

PDF CVPRW Semantic Scholar

Cite

Text

Yang. "Multi-Stage Optimization for Photorealistic Neural Style Transfer." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2019. doi:10.1109/CVPRW.2019.00227

Markdown

[Yang. "Multi-Stage Optimization for Photorealistic Neural Style Transfer." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2019.](https://mlanthology.org/cvprw/2019/yang2019cvprw-multistage/) doi:10.1109/CVPRW.2019.00227

BibTeX

@inproceedings{yang2019cvprw-multistage,
  title     = {{Multi-Stage Optimization for Photorealistic Neural Style Transfer}},
  author    = {Yang, Richard R.},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops},
  year      = {2019},
  pages     = {1769-1776},
  doi       = {10.1109/CVPRW.2019.00227},
  url       = {https://mlanthology.org/cvprw/2019/yang2019cvprw-multistage/}
}