Deformable Style Transfer

March 24, 2020 · Entered Twilight · 🏛 European Conference on Computer Vision

"Last commit was 5.0 years ago (≥5 year threshold)"

Evidence collected by the PWNC Scanner

Repo contents: NBB, README.md, cleanpoints.py, demo_DST.ipynb, demo_warp.ipynb, dst.bib, example, job_example.sh, loss.py, main.py, styletransfer.py, utils_keypoints.py, utils_misc.py, utils_plot.py, utils_pyr.py, utils_save.py, vggfeatures.py, warp.py

Authors Sunnie S. Y. Kim, Nicholas Kolkin, Jason Salavon, Gregory Shakhnarovich arXiv ID 2003.11038 Category cs.CV: Computer Vision Cross-listed cs.GR, cs.LG Citations 63 Venue European Conference on Computer Vision Repository https://github.com/sunniesuhyoung/DST ⭐ 266 Last Checked 1 month ago

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. Code has been made publicly available at https://github.com/sunniesuhyoung/DST.