Consistent Video Style Transfer via Compound Regularization


  • Wenjing Wang Peking University
  • Jizheng Xu ByteDance Inc.
  • Li Zhang ByteDance Inc.
  • Yue Wang ByteDance Inc.
  • Jiaying Liu Peking University



Recently, neural style transfer has drawn many attentions and significant progresses have been made, especially for image style transfer. However, flexible and consistent style transfer for videos remains a challenging problem. Existing training strategies, either using a significant amount of video data with optical flows or introducing single-frame regularizers, have limited performance on real videos. In this paper, we propose a novel interpretation of temporal consistency, based on which we analyze the drawbacks of existing training strategies; and then derive a new compound regularization. Experimental results show that the proposed regularization can better balance the spatial and temporal performance, which supports our modeling. Combining with the new cost formula, we design a zero-shot video style transfer framework. Moreover, for better feature migration, we introduce a new module to dynamically adjust inter-channel distributions. Quantitative and qualitative results demonstrate the superiority of our method over other state-of-the-art style transfer methods. Our project is publicly available at:




How to Cite

Wang, W., Xu, J., Zhang, L., Wang, Y., & Liu, J. (2020). Consistent Video Style Transfer via Compound Regularization. Proceedings of the AAAI Conference on Artificial Intelligence, 34(07), 12233-12240.



AAAI Technical Track: Vision