Deformable Style Transfer (ECCV 2020) - 10min Talk

ECCV 2020

Deformable Style Transfer (ECCV 2020) - 10min Talk

Aug 18, 2020
|
154 views
|
Details
Deformable Style Transfer (ECCV 2020) Sunnie S. Y. Kim, Nick Kolkin, Jason Salavon and Greg Shakhnarovich Project page: https://sunniesuhyoung.github.io/DST-page Paper: https://arxiv.org/abs/2003.11038 Code: https://github.com/sunniesuhyoung/DST Demo: https://bit.ly/DST-demo Abstract: Both geometry and texture are fundamental aspects of visual style. Existing style transfer methods, however, primarily focus on texture, almost entirely ignoring geometry. We propose deformable style transfer (DST), an optimization-based approach that jointly stylizes the texture and geometry of a content image to better match a style image. Unlike previous geometry-aware stylization methods, our approach is neither restricted to a particular domain (such as human faces), nor does it require training sets of matching style/content pairs. We demonstrate our method on a diverse set of content and style images including portraits, animals, objects, scenes, and paintings.

Comments
loading...