SinDDM:单图像去噪扩散模型
SinDDM: A Single Image Denoising Diffusion Model
AI总结:
本文提出 SinDDM 框架,利用多尺度扩散过程和轻量级全卷积去噪器在单张图像上训练 DDM,支持任意尺寸生成,并可通过 CLIP 实现文本引导及多种图像任务。
摘要:
去噪扩散模型(DDM)在图像生成、编辑和复原方面带来了惊人的性能飞跃。然而,现有的 DDM 使用非常大的数据集进行训练。在此,我们介绍一个在单张图像上训练 DDM 的框架。我们的方法命名为 SinDDM,通过使用多尺度扩散过程来学习训练图像的内部统计信息。为了驱动反向扩散过程,我们使用全卷积轻量级去噪器,该去噪器同时以噪声水平和尺度为条件。这种架构允许以由粗到细的方式生成任意维度的样本。正如我们所展示的,SinDDM 生成多样化的高质量样本,并适用于广泛的任务,包括风格迁移和图像协调。此外,它可以很容易地由外部监督引导。特别地,我们展示了使用预训练 CLIP 模型从单张图像进行文本引导生成。
英文摘要:
Denoising diffusion models (DDMs) have led to staggering performance leaps in image generation, editing and restoration. However, existing DDMs use very large datasets for training. Here, we introduce a framework for training a DDM on a single image. Our method, which we coin SinDDM, learns the internal statistics of the training image by using a multi-scale diffusion process. To drive the reverse diffusion process, we use a fully-convolutional light-weight denoiser, which is conditioned on both the noise level and the scale. This architecture allows generating samples of arbitrary dimensions, in a coarse-to-fine manner. As we illustrate, SinDDM generates diverse high-quality samples, and is applicable in a wide array of tasks, including style transfer and harmonization. Furthermore, it can be easily guided by external supervision. Particularly, we demonstrate text-guided generation from a single image using a pre-trained CLIP model.
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。