通用逼真风格迁移：一种轻量且自适应的方法
Universal Photorealistic Style Transfer: A Lightweight and Adaptive Approach
AI总结：
本文提出通用逼真风格迁移框架UPST，通过轻量级StyleNet和实例自适应优化，无需预训练即可在高分辨率图像和视频上实现色调准确、低内存占用的逼真风格迁移。
摘要：
逼真风格迁移旨在应用风格化的同时保留输入内容的真实感和结构。然而，现有方法常常面临诸如色调失真、依赖成对预训练、处理高分辨率输入时效率低下，以及在视频风格迁移任务中需要额外约束等挑战。为解决这些问题，我们提出了一种通用逼真风格迁移（UPST）框架，该框架无需依赖预训练即可在高分辨率图像和视频上实现精确的逼真风格迁移。我们的方法引入了一个轻量级的 StyleNet 用于逐实例迁移，在保证色调准确性的同时支持高分辨率输入，保持快速处理速度，并消除了预训练的需求。为了进一步增强逼真度和效率，我们引入了实例自适应优化，该优化采用自适应系数来优先保证内容图像的真实感，并使用早停法加速网络收敛。此外，由于 UPST 具有强大的非颜色信息保持能力，它能够无需额外约束即可实现无缝的视频风格迁移。实验结果表明，UPST 能够持续生成逼真的输出，并显著降低 GPU 内存占用，使其成为适用于各种逼真风格迁移任务的有效且通用的解决方案。
英文摘要：
Photorealistic style transfer aims to apply stylization while preserving the realism and structure of input content. However, existing methods often encounter challenges such as color tone distortions, dependency on pair-wise pre-training, inefficiency with high-resolution inputs, and the need for additional constraints in video style transfer tasks. To address these issues, we propose a Universal Photorealistic Style Transfer (UPST) framework that delivers accurate photorealistic style transfer on high-resolution images and videos without relying on pre-training. Our approach incorporates a lightweight StyleNet for per-instance transfer, ensuring color tone accuracy while supporting high-resolution inputs, maintaining rapid processing speeds, and eliminating the need for pretraining. To further enhance photorealism and efficiency, we introduce instance-adaptive optimization, which features an adaptive coefficient to prioritize content image realism and employs early stopping to accelerate network convergence. Additionally, UPST enables seamless video style transfer without additional constraints due to its strong non-color information preservation ability. Experimental results show that UPST consistently produces photorealistic outputs and significantly reduces GPU memory usage, making it an effective and universal solution for various photorealistic style transfer tasks.
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。
