Learning Selfie-Friendly Abstraction from Artistic Style Images

Yicun Liu, Jimmy Ren, Jianbo Liu, Xiaohao Chen
Proceedings of The 10th Asian Conference on Machine Learning, PMLR 95:113-128, 2018.

Abstract

Artistic style transfer can be thought as a process to generate different versions of abstraction of the original image. However, most of the artistic style transfer operators are not optimized for human faces thus mainly suffers from two undesirable features when applying them to selfies. First, the edges of human faces may unpleasantly deviate from the ones in the original image. Second, the skin color is far from faithful to the original one which is usually problematic in producing quality selfies. In this paper, we take a different approach and formulate this abstraction process as a gradient domain learning problem. We aim to learn a type of abstraction which not only achieves the specified artistic style but also circumvents the two aforementioned drawbacks thus highly applicable to selfie photography. We also show that our method can be directly generalized to videos with high inter-frame consistency. Our method is also robust to non-selfie images, and the generalization to various kinds of real-life scenes is discussed. We will make our code publicly available.

Cite this Paper

BibTeX
@InProceedings{pmlr-v95-liu18a, title = {Learning Selfie-Friendly Abstraction from Artistic Style Images}, author = {Liu, Yicun and Ren, Jimmy and Liu, Jianbo and Chen, Xiaohao}, booktitle = {Proceedings of The 10th Asian Conference on Machine Learning}, pages = {113--128}, year = {2018}, editor = {Zhu, Jun and Takeuchi, Ichiro}, volume = {95}, series = {Proceedings of Machine Learning Research}, month = {14--16 Nov}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v95/liu18a/liu18a.pdf}, url = {https://proceedings.mlr.press/v95/liu18a.html}, abstract = {Artistic style transfer can be thought as a process to generate different versions of abstraction of the original image. However, most of the artistic style transfer operators are not optimized for human faces thus mainly suffers from two undesirable features when applying them to selfies. First, the edges of human faces may unpleasantly deviate from the ones in the original image. Second, the skin color is far from faithful to the original one which is usually problematic in producing quality selfies. In this paper, we take a different approach and formulate this abstraction process as a gradient domain learning problem. We aim to learn a type of abstraction which not only achieves the specified artistic style but also circumvents the two aforementioned drawbacks thus highly applicable to selfie photography. We also show that our method can be directly generalized to videos with high inter-frame consistency. Our method is also robust to non-selfie images, and the generalization to various kinds of real-life scenes is discussed. We will make our code publicly available.} }
Endnote
%0 Conference Paper %T Learning Selfie-Friendly Abstraction from Artistic Style Images %A Yicun Liu %A Jimmy Ren %A Jianbo Liu %A Xiaohao Chen %B Proceedings of The 10th Asian Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2018 %E Jun Zhu %E Ichiro Takeuchi %F pmlr-v95-liu18a %I PMLR %P 113--128 %U https://proceedings.mlr.press/v95/liu18a.html %V 95 %X Artistic style transfer can be thought as a process to generate different versions of abstraction of the original image. However, most of the artistic style transfer operators are not optimized for human faces thus mainly suffers from two undesirable features when applying them to selfies. First, the edges of human faces may unpleasantly deviate from the ones in the original image. Second, the skin color is far from faithful to the original one which is usually problematic in producing quality selfies. In this paper, we take a different approach and formulate this abstraction process as a gradient domain learning problem. We aim to learn a type of abstraction which not only achieves the specified artistic style but also circumvents the two aforementioned drawbacks thus highly applicable to selfie photography. We also show that our method can be directly generalized to videos with high inter-frame consistency. Our method is also robust to non-selfie images, and the generalization to various kinds of real-life scenes is discussed. We will make our code publicly available.
APA
Liu, Y., Ren, J., Liu, J. & Chen, X.. (2018). Learning Selfie-Friendly Abstraction from Artistic Style Images. Proceedings of The 10th Asian Conference on Machine Learning, in Proceedings of Machine Learning Research 95:113-128 Available from https://proceedings.mlr.press/v95/liu18a.html.

Related Material