Towards Efficient Image and Video Style Transfer via Distillation and Learnable Feature Transformation

Jing Huo¹,

Meihao Kong¹,

Wenbin Li¹,

Jing Wu²,

Yu-Kun Lai²,

Yang Gao¹,

¹NanJing University ²Cardiff University

Paper arXiv Code & Data

Upper-Left-Corner: Original Video; Lower-Left-Corner: Style Image; Right: Our Result

@misc{huo22,
      title={Towards Efficient Image and Video Style Transfer via Distillation and Learnable Feature Transformation}, 
      author={Jing Huo and Meihao Kong and Wenbin Li and Jing Wu and Yu-Kun Lai and Yang Gao},
      year={2022}
}

Acknowledgements: This work is supported by Science and Technology Innovation 2030 New Generation Artificial Intelligence Major Project (2021ZD0113303), the National Natural Science Foundation of China (61806092, 62106100, 62192783), the CAAI-Huawei MindSpore Open Fund and the Collaborative Innovation Center of Novel Software Technology and Industrialization.