STALP: Style Transfer with Auxiliary Limited Pairing. (4th June 2021)

• Record Type: Journal Article
• Authors: Futschik, D.; Kučera, M.; Lukáč, M.; Wang, Z.; Shechtman, E.; Sýkora, D.
• Is Part Of: Computer graphics forum. Volume 40:Number 2(2021)
• Page Start: 563
• Page End: 573
• Publication Date: 2021-06-04
• Subjects: Computing methodologies -- → Non‐photorealistic rendering; Computer graphics -- Periodicals; 006.605
• DOI: 10.1111/cgf.142655
• Languages: English
• ISSNs: 0167-7055

Abstract

Abstract: We present an approach to example‐based stylization of images that uses a single pair of a source image and its stylized counterpart. We demonstrate how to train an image translation network that can perform real‐time semantically meaningful style transfer to a set of target images with similar content as the source image. A key added value of our approach is that it considers also consistency of target images during training. Although those have no stylized counterparts, we constrain the translation to keep the statistics of neural responses compatible with those extracted from the stylized source. In contrast to concurrent techniques that use a similar input, our approach better preserves important visual characteristics of the source style and can deliver temporally stable results without the need to explicitly handle temporal consistency. We demonstrate its practical utility on various applications including video stylization, style transfer to panoramas, faces, and 3D models.