ArtFlow: Unbiased Image Style Transfer via Reversible Neural Flows

Universal style transfer retains styles from reference images in content images. While existing methods have achieved state-of-the-art style transfer performance, they are not aware of the content leak phenomenon that the image content may corrupt after several rounds of stylization process. In this...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Proceedings (IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Online) s. 862 - 871
Hlavní autoři: An, Jie, Huang, Siyu, Song, Yibing, Dou, Dejing, Liu, Wei, Luo, Jiebo
Médium: Konferenční příspěvek
Jazyk:angličtina
Vydáno: IEEE 01.06.2021
Témata:
Computer vision
Feature extraction
Inference algorithms
Neural networks
Pattern recognition
ISSN:1063-6919
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:Universal style transfer retains styles from reference images in content images. While existing methods have achieved state-of-the-art style transfer performance, they are not aware of the content leak phenomenon that the image content may corrupt after several rounds of stylization process. In this paper, we propose ArtFlow to prevent content leak during universal style transfer. ArtFlow consists of reversible neural flows and an unbiased feature transfer module. It supports both forward and backward inferences and operates in a projection-transfer-reversion scheme. The forward inference projects input images into deep features, while the backward inference remaps deep features back to input images in a lossless and unbiased way. Extensive experiments demonstrate that ArtFlow achieves comparable performance to state-of-the-art style transfer methods while avoiding content leak.
ISSN:1063-6919
DOI:10.1109/CVPR46437.2021.00092