DreamSampler：统一扩散采样与分数蒸馏以进行图像处理
DreamSampler: Unifying Diffusion Sampling and Score Distillation for Image Manipulation
AI总结：
本文提出DreamSampler框架，通过正则化潜在优化将逆向扩散采样与分数蒸馏无缝集成，解决现有方法需调整架构或易模式崩溃的问题，实现图像编辑与重建。
摘要：
近年来，逆向采样和分数蒸馏已成为使用潜在扩散模型（LDMs）进行图像处理的主要工具。虽然逆向扩散采样通常需要调整LDM架构或进行特征工程，但分数蒸馏提供了一种简单而强大的模型无关方法，不过它往往容易出现模式崩溃。为了解决这些限制并发挥两种方法的优势，我们在此引入了一个名为DreamSampler的新颖框架，该框架通过正则化潜在优化的视角，将这两种不同的方法无缝集成。与分数蒸馏类似，DreamSampler是一种模型无关的方法，适用于任何LDM架构，但它允许在图像编辑和重建的额外引导下进行蒸馏和逆向采样。通过涉及图像编辑、SVG重建等实验，我们证明了DreamSampler与现有方法相比具有竞争力的性能，同时提供了新的应用。代码：https://github.com/DreamSampler/dream-sampler
英文摘要：
Reverse sampling and score-distillation have emerged as main workhorses in recent years for image manipulation using latent diffusion models (LDMs). While reverse diffusion sampling often requires adjustments of LDM architecture or feature engineering, score distillation offers a simple yet powerful model-agnostic approach, but it is often prone to mode-collapsing. To address these limitations and leverage the strengths of both approaches, here we introduce a novel framework called {\em DreamSampler}, which seamlessly integrates these two distinct approaches through the lens of regularized latent optimization. Similar to score-distillation, DreamSampler is a model-agnostic approach applicable to any LDM architecture, but it allows both distillation and reverse sampling with additional guidance for image editing and reconstruction. Through experiments involving image editing, SVG reconstruction and etc, we demonstrate the competitive performance of DreamSampler compared to existing approaches, while providing new applications. Code: https://github.com/DreamSampler/dream-sampler
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。
