paper note

Exemplar-guided Image Translation

Task: Each exemplar represents one domain. Transfer the style of exemplar image to the input image.

[1]

  • reconstruct the style code: [2]

  • use pretrained network (prior knowledge) to extract the style code: [3]

Reference

  1. Zhang, Pan, et al. “Cross-domain correspondence learning for exemplar-based image translation.” CVPR, 2020.

  2. Anokhin, Ivan, et al. “High-resolution daytime translation without domain labels.” CVPR, 2020.

  3. Tumanyan, Narek, et al. “Splicing ViT Features for Semantic Appearance Transfer.” CVPR, 2022.