FastCLIPstyler：利用风格表示实现无需优化的基于文本的图像风格迁移
FastCLIPstyler: Optimisation-free Text-based Image Style Transfer Using Style Representations
AI总结：
针对 CLIPstyler 每查询需冗长优化的问题，本文提出 FastCLIPstyler 与轻量 EdgeCLIPstyler，实现单次前向传播的文本图像风格迁移，并在质量和运行效率上优于现有方法。
摘要：
近年来，语言驱动的艺术风格迁移作为一种新型风格迁移技术兴起，它通过使用风格的自然语言描述，消除了对参考风格图像的需求。首个实现这一目标的模型名为 CLIPstyler，已展示出令人印象深刻的风格化效果。然而，它在运行时针对每个查询都需要冗长的优化过程，这限制了其在许多实际应用中的适用性。在本工作中，我们提出 FastCLIPstyler，这是一种通用的基于文本的图像风格迁移模型，能够针对任意文本输入在单次前向传播中完成图像风格化。此外，我们还提出 EdgeCLIPstyler，这是一种为兼容资源受限设备而设计的轻量级模型。通过与最先进方法进行定量和定性比较，我们证明，基于可测量指标，我们的模型取得了更优的风格化质量，同时运行时效率显著提高，尤其是在边缘设备上。
英文摘要：
In recent years, language-driven artistic style transfer has emerged as a new type of style transfer technique, eliminating the need for a reference style image by using natural language descriptions of the style. The first model to achieve this, called CLIPstyler, has demonstrated impressive stylisation results. However, its lengthy optimisation procedure at runtime for each query limits its suitability for many practical applications. In this work, we present FastCLIPstyler, a generalised text-based image style transfer model capable of stylising images in a single forward pass for arbitrary text inputs. Furthermore, we introduce EdgeCLIPstyler, a lightweight model designed for compatibility with resource-constrained devices. Through quantitative and qualitative comparisons with state-of-the-art approaches, we demonstrate that our models achieve superior stylisation quality based on measurable metrics while offering significantly improved runtime efficiency, particularly on edge devices.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
