用强化学习实现轻量级任意风格迁移，生成流畅艺术序列
RLMiniStyler: Light-weight RL Style Agent for Arbitrary Sequential Neural Style Generation
- 基于强化学习策略迭代优化风格迁移过程
- 在多分辨率下实现高质量多样风格序列生成，计算成本更低
- 适合需要低资源部署的图像风格化应用
任意风格迁移旨在将任意艺术图像的风格应用于另一内容图像。然而，现有深度学习方法常需大量计算资源以生成多样化结果。为此，我们提出一种基于强化学习的轻量级框架 RLMiniStyler。该框架通过统一的强化学习策略，利用风格化反馈进行探索与利用，迭代引导风格迁移过程，生成平滑连续的风格化结果，同时保持模型轻量化。此外，引入不确定性感知的多任务学习策略，自动调整损失权重以适应不同训练阶段的内容-风格平衡需求，从而加速模型收敛。在多种图像分辨率上的实验验证表明，相较于其他先进方法，RLMiniStyler 在更低计算成本下实现了高质量、多样化的艺术图像序列生成。代码已开源：https://github.com/fengxiaoming520/RLMiniStyler。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。