CustAny：从单一示例定制任意对象
CustAny: Customizing Anything from A Single Example
AI总结：
本文提出CustAny零样本框架和MC-IDC大规模数据集，通过通用ID提取、双层级ID注入和ID感知解耦，实现从单一示例对任意对象进行身份保持的灵活定制。
摘要：
近年来，基于扩散的文本到图像模型的发展简化了高保真图像的生成，但保持特定元素（如一只个人宠物狗）的身份（ID）仍然具有挑战性。对象定制利用参考图像和文本描述，是解决这一问题的关键。当前的对象定制方法要么是对象特定的，需要大量微调；要么是对象无关的，提供零样本定制但仅限于特定领域。将零样本对象定制从特定领域推广到通用领域的核心问题是建立一个大规模通用ID数据集用于模型预训练，而这一过程耗时且费力。本文提出了一种新流程来构建大规模通用对象数据集，并构建了多类别ID一致性（MC-IDC）数据集，该数据集包含315k个文本-图像样本，覆盖10k个类别。借助MC-IDC，我们提出了Customizing Anything（CustAny），这是一个零样本框架，能够保持ID保真度并支持对通用对象进行灵活的文本编辑。CustAny包含三个关键组件：通用ID提取模块、双层级ID注入模块和ID感知解耦模块，使其能够从单一参考图像和文本提示中定制任意对象。实验表明，CustAny在通用对象定制以及人类定制和虚拟试穿等专业领域均优于现有方法。我们的贡献包括大规模数据集、CustAny框架以及新颖的ID处理方法，以推动该领域的发展。代码和数据集将很快在https://github.com/LingjieKong-fdu/CustAny发布。
英文摘要：
Recent advances in diffusion-based text-to-image models have simplified creating high-fidelity images, but preserving the identity (ID) of specific elements, like a personal dog, is still challenging. Object customization, using reference images and textual descriptions, is key to addressing this issue. Current object customization methods are either object-specific, requiring extensive fine-tuning, or object-agnostic, offering zero-shot customization but limited to specialized domains. The primary issue of promoting zero-shot object customization from specific domains to the general domain is to establish a large-scale general ID dataset for model pre-training, which is time-consuming and labor-intensive. In this paper, we propose a novel pipeline to construct a large dataset of general objects and build the Multi-Category ID-Consistent (MC-IDC) dataset, featuring 315k text-image samples across 10k categories. With the help of MC-IDC, we introduce Customizing Anything (CustAny), a zero-shot framework that maintains ID fidelity and supports flexible text editing for general objects. CustAny features three key components: a general ID extraction module, a dual-level ID injection module, and an ID-aware decoupling module, allowing it to customize any object from a single reference image and text prompt. Experiments demonstrate that CustAny outperforms existing methods in both general object customization and specialized domains like human customization and virtual try-on. Our contributions include a large-scale dataset, the CustAny framework and novel ID processing to advance this field. Code and dataset will be released soon in https://github.com/LingjieKong-fdu/CustAny.
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。
