匹配与融合：从无结构图像集实现一致生成
Match-and-Fuse: Consistent Generation from Unstructured Image Sets
AI总结：
本文提出Match-and-Fuse方法，通过图模型实现无结构图像集的一致生成，利用内部特征融合和密集输入对应关系，在无需掩码或人工监督的情况下生成一致且高质量的图像集。
摘要：
我们提出了Match-and-Fuse——一种零样本、无需训练的方法，用于一致可控生成无结构图像集——即共享共同视觉元素但视角、拍摄时间和周围内容不同的集合。与现有方法不同，我们的框架实现集到集的生成：给定源集和用户提示，它生成一个新的集，以保持共享内容的跨图像一致性。我们的核心思想是将任务建模为图，其中每个节点对应一张图像，每条边触发图像对的联合生成。这种建模将所有成对生成整合到统一框架中，通过在图像对之间融合内部特征，利用密集输入对应关系，在无需掩码或人工监督的情况下，确保局部一致性并保证整个集的全局一致性。这通过利用文本到图像模型中涌现的先验知识实现，该先验知识在多个视角共享单个画布时鼓励一致的生成。Match-and-Fuse实现了最先进的一致性和视觉质量，并解锁了从图像集创建内容的新能力。
英文摘要：
We present Match-and-Fuse - a zero-shot, training-free method for consistent controlled generation of unstructured image sets - collections that share a common visual element, yet differ in viewpoint, time of capture, and surrounding content. Unlike existing methods that operate on individual images or densely sampled videos, our framework performs set-to-set generation: given a source set and user prompts, it produces a new set that preserves cross-image consistency of shared content. Our key idea is to model the task as a graph, where each node corresponds to an image and each edge triggers a joint generation of image pairs. This formulation consolidates all pairwise generations into a unified framework, enforcing local consistency while ensuring global coherence across the entire set. This is achieved by fusing internal features across image pairs, guided by dense input correspondences, without requiring masks or manual supervision, and by leveraging an emergent prior in text-to-image models that encourages coherent generation when multiple views share a single canvas. Match-and-Fuse achieves state-of-the-art consistency and visual quality, and unlocks new capabilities for content creation from image collections.
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。
