Generating images by example of segmentation mask, edge, or pose

  • 0 Replies
  • 79 Views
*

ivan.moony

  • Trusty Member
  • ***********
  • Eve
  • *
  • 1412
    • e-teoria
Cross-domain Correspondence Learning for Exemplar-based Image Translation

Source: medium.com (there are links to scientific paper and project home page)

Quote


We propose an exemplar-based image synthesis. Given the exemplar images (1st row), our network translates the inputs in the form of segmentation mask, edge and pose, to photorealistic images (2nd row) under the guidance of dense correspondence to the exemplar image.
« Last Edit: May 22, 2020, 01:01:09 PM by ivan.moony »
There exist some rules interwoven within this world. As much as it is a blessing, so much it is a curse.

 


Users Online

76 Guests, 0 Users

Most Online Today: 88. Most Online Ever: 340 (March 26, 2019, 09:47:57 PM)

Articles