RLMiniStyler: Light-weight RL Style Agent for Arbitrary Sequential Neural Style Generation
This work addresses computational efficiency for users in image processing and artistic applications, though it appears incremental by building on existing deep learning methods.
The paper tackles the problem of high computational costs in arbitrary style transfer by proposing RLMiniStyler, a reinforcement learning-based framework that generates diverse, high-quality stylized image sequences at lower cost, as validated through experiments across various resolutions.
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.