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 this https URL.
Abstract (translated)
任意风格转换的目标是将给定的艺术图像的风格应用到另一张内容图上。然而，现有的基于深度学习的方法通常需要较大的计算成本来生成多样化的风格化结果。鉴于此，我们提出了一种新颖的强化学习框架RLMiniStyler用于任意风格转移。该框架利用统一的强化学习策略迭代地引导风格转换过程，通过探索和利用风格化反馈，从而在实现模型轻量化的同时生成平滑连续的风格化结果序列。 此外，我们引入了基于不确定性的多任务学习策略，这种策略可以自动调整损失权重以适应不同训练阶段的内容与风格平衡需求，从而加速模型收敛。通过一系列跨图像分辨率的实验，我们在RLMiniStyler与其他最新方法之间验证了其在低成本下生成高质量、多样化艺术图序列的优势。 代码可以在提供的链接处获取：[此URL]（请将括号内的内容替换为实际链接）。
URL
https://arxiv.org/abs/2505.04424
