Style-A-Video：基于任意文本的视频风格迁移的敏捷扩散方法
Style-A-Video: Agile Diffusion for Arbitrary Text-based Video Style Transfer
AI总结：
本文提出Style-A-Video，一种零样本视频风格化方法，利用生成式预训练Transformer和图像潜扩散模型，通过改进引导条件、采样优化和时间一致性模块，实现文本控制的视频风格迁移，在保持内容的同时降低资源消耗。
摘要：
大规模文本到视频扩散模型已展现出合成多样化视频的卓越能力。然而，由于缺乏广泛的文本到视频数据集以及训练所需的计算资源，直接应用这些模型进行视频风格化仍然困难。此外，由于对输入内容的噪声添加过程是随机且具有破坏性的，满足风格迁移任务的内容保持标准颇具挑战。本文提出了一种名为Style-A-Video的零样本视频风格化方法，该方法利用生成式预训练Transformer与图像潜扩散模型，实现简洁的文本控制的视频风格化。我们改进了去噪过程中的引导条件，在艺术表达与结构保持之间建立了平衡。此外，为了减少帧间闪烁并避免额外伪影的形成，我们采用了采样优化和时间一致性模块。大量实验表明，与先前解决方案相比，我们能够在获得更优的内容保持和风格表现的同时，消耗更少的资源。代码将在https://github.com/haha-lisa/Style-A-Video提供。
英文摘要：
Large-scale text-to-video diffusion models have demonstrated an exceptional ability to synthesize diverse videos. However, due to the lack of extensive text-to-video datasets and the necessary computational resources for training, directly applying these models for video stylization remains difficult. Also, given that the noise addition process on the input content is random and destructive, fulfilling the style transfer task's content preservation criteria is challenging. This paper proposes a zero-shot video stylization method named Style-A-Video, which utilizes a generative pre-trained transformer with an image latent diffusion model to achieve a concise text-controlled video stylization. We improve the guidance condition in the denoising process, establishing a balance between artistic expression and structure preservation. Furthermore, to decrease inter-frame flicker and avoid the formation of additional artifacts, we employ a sampling optimization and a temporal consistency module. Extensive experiments show that we can attain superior content preservation and stylistic performance while incurring less consumption than previous solutions. Code will be available at https://github.com/haha-lisa/Style-A-Video.
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。
