Dynamic Instance Normalization for Arbitrary Style Transfer


  • Yongcheng Jing Zhejiang University
  • Xiao Liu Baidu Inc.
  • Yukang Ding Baidu Inc.
  • Xinchao Wang Stevens Institute of Technology
  • Errui Ding Baidu Inc.
  • Mingli Song Zhejiang University
  • Shilei Wen Baidu Inc.




Prior normalization methods rely on affine transformations to produce arbitrary image style transfers, of which the parameters are computed in a pre-defined way. Such manually-defined nature eventually results in the high-cost and shared encoders for both style and content encoding, making style transfer systems cumbersome to be deployed in resource-constrained environments like on the mobile-terminal side. In this paper, we propose a new and generalized normalization module, termed as Dynamic Instance Normalization (DIN), that allows for flexible and more efficient arbitrary style transfers. Comprising an instance normalization and a dynamic convolution, DIN encodes a style image into learnable convolution parameters, upon which the content image is stylized. Unlike conventional methods that use shared complex encoders to encode content and style, the proposed DIN introduces a sophisticated style encoder, yet comes with a compact and lightweight content encoder for fast inference. Experimental results demonstrate that the proposed approach yields very encouraging results on challenging style patterns and, to our best knowledge, for the first time enables an arbitrary style transfer using MobileNet-based lightweight architecture, leading to a reduction factor of more than twenty in computational cost as compared to existing approaches. Furthermore, the proposed DIN provides flexible support for state-of-the-art convolutional operations, and thus triggers novel functionalities, such as uniform-stroke placement for non-natural images and automatic spatial-stroke control.




How to Cite

Jing, Y., Liu, X., Ding, Y., Wang, X., Ding, E., Song, M., & Wen, S. (2020). Dynamic Instance Normalization for Arbitrary Style Transfer. Proceedings of the AAAI Conference on Artificial Intelligence, 34(04), 4369-4376. https://doi.org/10.1609/aaai.v34i04.5862



AAAI Technical Track: Machine Learning