TY - GEN
T1 - RLMiniStyler
T2 - 34th Internationa Joint Conference on Artificial Intelligence, IJCAI 2025
AU - Hu, Jing
AU - Feng, Chengming
AU - Hu, Shu
AU - Chang, Ming Ching
AU - Li, Xin
AU - Wu, Xi
AU - Wang, Xin
N1 - Publisher Copyright: © 2025 International Joint Conferences on Artificial Intelligence. All rights reserved.
PY - 2025
Y1 - 2025
N2 - 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.
AB - 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.
UR - https://www.scopus.com/pages/publications/105021814315
U2 - 10.24963/ijcai.2025/125
DO - 10.24963/ijcai.2025/125
M3 - Conference contribution
T3 - IJCAI International Joint Conference on Artificial Intelligence
SP - 1116
EP - 1124
BT - Proceedings of the 34th International Joint Conference on Artificial Intelligence, IJCAI 2025
A2 - Kwok, James
PB - International Joint Conferences on Artificial Intelligence
Y2 - 16 August 2025 through 22 August 2025
ER -