Skip to main navigation Skip to search Skip to main content

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

  • Chengdu University of Information Technology
  • Purdue University

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

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.

Original languageEnglish
Title of host publicationProceedings of the 34th International Joint Conference on Artificial Intelligence, IJCAI 2025
EditorsJames Kwok
PublisherInternational Joint Conferences on Artificial Intelligence
Pages1116-1124
Number of pages9
ISBN (Electronic)9781956792065
DOIs
StatePublished - 2025
Event34th Internationa Joint Conference on Artificial Intelligence, IJCAI 2025 - Montreal, Canada
Duration: Aug 16 2025Aug 22 2025

Publication series

NameIJCAI International Joint Conference on Artificial Intelligence

Conference

Conference34th Internationa Joint Conference on Artificial Intelligence, IJCAI 2025
Country/TerritoryCanada
CityMontreal
Period08/16/2508/22/25

Fingerprint

Dive into the research topics of 'RLMiniStyler: Light-weight RL Style Agent for Arbitrary Sequential Neural Style Generation'. Together they form a unique fingerprint.

Cite this