One-Shot Stylization for Full-Body Human Images
University of Illinois Urbana-Champaign
- [04/2023] We plan to release code soon here.
- [04/2023] Paper released on arXiv here.
The goal of human stylization is to transfer full-body human photos to a style specified by a single art character reference image.
Although previous work has succeeded in example-based stylization of faces and generic scenes, full-body human stylization is a more complex domain.
This work addresses several unique challenges of stylizing full-body human images.
We propose a method for one-shot fine-tuning of a pose-guided human generator to preserve the "content"
(garments, face, hair, pose) of the input photo and the "style" of the artistic reference.
Since body shape deformation is an essential component of an art character's style,
we incorporate a novel skeleton deformation module to reshape the pose of the input person and modify the
pose-guided person generator
to be more robust to the rescaled poses falling outside the distribution of the realistic poses
the generator is originally trained on.
Several human studies verify the effectiveness of our approach.
We can inherit the editing applications from the base models.
We can achieve virtual try-on on stylized human subjects.
Pose Transfer can be performed for art characters.
Thanks to Unnat Jain for sharing the template of this project page.