Proceedings

RLMiniStyler: Light-weight RL Style Agent for Arbitrary Sequential Neural Style Generation

Jing Hu, Chengming Feng, Shu Hu, Ming-Ching Chang, Xin Li, Xi Wu, Xin Wang

Download BibTeX Cite

Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence. Main Track. Pages 1116-1124.

https://doi.org/10.24963/ijcai.2025/125

Keywords

  • Computer Vision: CV: Efficiency and Optimization
  • Computer Vision: CV: Applications and Systems
  • Multidisciplinary Topics and Applications: MTA: Arts and creativity
  • Computer Vision: CV: Image and video synthesis and generation

Abstract

Arbitrary style transfer aims to apply the style of any given artistic image to another content image. Still, existing deep learning-based methods often require significant computational costs to generate diverse stylized results. Motivated by this, we propose a novel reinforcement learning-based framework for arbitrary style transfer RLMiniStyler. This framework leverages a unified reinforcement learning policy to iteratively guide the style transfer process by exploring and exploiting stylization feedback, generating smooth sequences of stylized results while achieving model lightweight. Furthermore, we introduce an uncertainty-aware multi-task learning strategy that automatically adjusts loss weights to adapt to the content and style balance requirements at different training stages, thereby accelerating model convergence. Through a series of experiments across image various resolutions, we have validated the advantages of RLMiniStyler over other state-of-the-art methods in generating high-quality, diverse artistic image sequences at a lower cost. Codes are available at https://github.com/fengxiaoming520/RLMiniStyler.

Jing Hu, Chengming Feng, Shu Hu, Ming-Ching Chang, Xin Li, Xi Wu, and Xin Wang. 2025. RLMiniStyler: Light-weight RL Style Agent for Arbitrary Sequential Neural Style Generation. In Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence, IJCAI-25. IJCAI, 1116–1124. https://doi.org/10.24963/ijcai.2025/125
Welcome Future Conferences AI Journal Division IJCAI Proceedings About IJCAI IJCAI Awards