Arbitrary-Scale Image Synthesis

Evangelos Ntavelis, Mohamad Shahbazi, Iason Kastanis, Radu Timofte, Martin Danelljan, Luc Van Gool

CVPR 2022 pp. 11533-11542

doi:10.1109/CVPR52688.2022.01124 /cvpr/2022/ntavelis2022cvpr-arbitraryscale/

Abstract

Positional encodings have enabled recent works to train a single adversarial network that can generate images of different scales. However, these approaches are either limited to a set of discrete scales or struggle to maintain good perceptual quality at the scales for which the model is not trained explicitly. We propose the design of scale-consistent positional encodings invariant to our generator's layers transformations. This enables the generation of arbitrary-scale images even at scales unseen during training. Moreover, we incorporate novel inter-scale augmentations into our pipeline and partial generation training to facilitate the synthesis of consistent images at arbitrary scales. Lastly, we show competitive results for a continuum of scales on various commonly used datasets for image synthesis.

PDF CVPR Semantic Scholar

Cite

Text

Ntavelis et al. "Arbitrary-Scale Image Synthesis." Conference on Computer Vision and Pattern Recognition, 2022. doi:10.1109/CVPR52688.2022.01124

Markdown

[Ntavelis et al. "Arbitrary-Scale Image Synthesis." Conference on Computer Vision and Pattern Recognition, 2022.](https://mlanthology.org/cvpr/2022/ntavelis2022cvpr-arbitraryscale/) doi:10.1109/CVPR52688.2022.01124

BibTeX

@inproceedings{ntavelis2022cvpr-arbitraryscale,
  title     = {{Arbitrary-Scale Image Synthesis}},
  author    = {Ntavelis, Evangelos and Shahbazi, Mohamad and Kastanis, Iason and Timofte, Radu and Danelljan, Martin and Van Gool, Luc},
  booktitle = {Conference on Computer Vision and Pattern Recognition},
  year      = {2022},
  pages     = {11533-11542},
  doi       = {10.1109/CVPR52688.2022.01124},
  url       = {https://mlanthology.org/cvpr/2022/ntavelis2022cvpr-arbitraryscale/}
}