FastBlend: Enhancing Video Stylization Consistency via Model-Free Patch Blending

Duan, Zhongjie; Wang, Chengyu; Chen, Cen; Qian, Weining; Huang, Jun; Jin, Mingyi

doi:10.24963/ijcai.2025/1119

FastBlend: Enhancing Video Stylization Consistency via Model-Free Patch Blending

Zhongjie Duan, Chengyu Wang, Cen Chen, Weining Qian, Jun Huang, Mingyi Jin

Download BibTeX Cite

Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence. AI, Arts & Creativity. Pages 10072-10080.

https://doi.org/10.24963/ijcai.2025/1119

Keywords

Application domains: Images, movies and visual arts

Abstract

With the emergence of diffusion models and the rapid development of image processing, generating artistic images in style transfer tasks has become effortless. However, these impressive image processing approaches face consistency issues in video processing due to the independent processing of each frame. In this paper, we propose a powerful, model-free approach called FastBlend to address the consistency problem in video stylization. FastBlend functions as a post-processor and can be seamlessly integrated with diffusion models to create a robust video stylization pipeline. Based on a patch-matching algorithm, we remap and blend the aligned content across multiple frames, thus compensating for inconsistent content with neighboring frames. Moreover, we propose a tree-like data structure and a specialized loss function, aiming to optimize computational efficiency and visual quality for different application scenarios. Extensive experiments have demonstrated the effectiveness of FastBlend. Compared with both independent video deflickering algorithms and diffusion-based video processing methods, FastBlend is capable of synthesizing more coherent and realistic videos.

Zhongjie Duan, Chengyu Wang, Cen Chen, Weining Qian, Jun Huang, and Mingyi Jin. 2025. FastBlend: Enhancing Video Stylization Consistency via Model-Free Patch Blending. In Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence, IJCAI-25. IJCAI, 10072–10080. https://doi.org/10.24963/ijcai.2025/1119

@inproceedings{ijcai2025p1119,
  title     = {FastBlend: Enhancing Video Stylization Consistency via Model-Free Patch Blending},
  author    = {Duan, Zhongjie and Wang, Chengyu and Chen, Cen and Qian, Weining and Huang, Jun and Jin, Mingyi},
  booktitle = {Proceedings of the Thirty-Fourth International Joint Conference on
               Artificial Intelligence, {IJCAI-25}},
  publisher = {International Joint Conferences on Artificial Intelligence Organization},
  editor    = {James Kwok},
  pages     = {10072--10080},
  year      = {2025},
  month     = {8},
  note      = {AI, Arts & Creativity},
  doi       = {10.24963/ijcai.2025/1119},
  url       = {https://doi.org/10.24963/ijcai.2025/1119},
}

TY  - CPAPER
TI  - FastBlend: Enhancing Video Stylization Consistency via Model-Free Patch Blending
AU  - Duan, Zhongjie
AU  - Wang, Chengyu
AU  - Chen, Cen
AU  - Qian, Weining
AU  - Huang, Jun
AU  - Jin, Mingyi
T2  - Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence, IJCAI-25
PB  - International Joint Conferences on Artificial Intelligence Organization
PY  - 2025
SP  - 10072
EP  - 10080
DO  - 10.24963/ijcai.2025/1119
UR  - https://doi.org/10.24963/ijcai.2025/1119
ER  -