基于关键点引导的扩散模型可变形图像处理
Key-point Guided Deformable Image Manipulation Using Diffusion Model
AI总结：
本文提出关键点引导的扩散模型（KDM），通过光流中间输出实现精确图像控制，在面部生成、姿态合成和超声预测中优于现有模型。
摘要：
本文提出了一种关键点引导的扩散概率模型（KDM），通过操纵对象的关键点来实现对图像的精确控制。我们提出了一种两阶段生成模型，将光流图作为中间输出。通过这种方式，建立了图像与稀疏关键点之间语义关系的密集像素级理解，从而实现更逼真的图像生成。此外，光流的整合有助于调节序列图像的帧间方差，展示了真实的序列图像生成能力。KDM在多种关键点条件图像合成任务上进行了评估，包括面部图像生成、人体姿态合成和超声心动图视频预测，结果表明与最先进的模型相比，KDM在一致性和逼真度方面均有提升。
英文摘要：
In this paper, we introduce a Key-point-guided Diffusion probabilistic Model (KDM) that gains precise control over images by manipulating the object's key-point. We propose a two-stage generative model incorporating an optical flow map as an intermediate output. By doing so, a dense pixel-wise understanding of the semantic relation between the image and sparse key point is configured, leading to more realistic image generation. Additionally, the integration of optical flow helps regulate the inter-frame variance of sequential images, demonstrating an authentic sequential image generation. The KDM is evaluated with diverse key-point conditioned image synthesis tasks, including facial image generation, human pose synthesis, and echocardiography video prediction, demonstrating the KDM is proving consistency enhanced and photo-realistic images compared with state-of-the-art models.
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。
