从个人相册中自动找相似照片，修复遮挡人脸。
AlbumFill: Album-Guided Reasoning and Retrieval for Personalized Image Completion
- 用视觉语言模型从相册检索身份一致的参考图
- 在54K人像数据集上显著提升修复一致性
- 适合需要保护个人形象的图像修复场景
个性化图像修复旨在恢复个人照片中被遮挡区域的同时保持身份与外观一致性。现有方法或依赖通用修复模型，难以维持身份连贯性；或假设存在明确提供的参考图像，但在实际中参考图常未显式给出，需系统从个人相册中搜索身份一致的图像。本文提出AlbumFill，一种无需训练的框架，可从个人相册中检索身份一致的参考图像以支持个性化修复。给定一张遮挡图像和一个个人相册，视觉语言模型推断缺失语义线索以指导组合式图像检索，检索到的参考图像再由基于参考的修复模型使用。为支持该任务，我们构建了一个包含54,000个以人物为中心样本及关联相册图像的数据集。多个基线实验表明个性化修复的挑战性，并凸显身份一致参考检索的重要性。
原文摘要 · Abstract (English)
Personalized image completion aims to restore occluded regions in personal photos while preserving identity and appearance. Existing methods either rely on generic inpainting models that often fail to maintain identity consistency, or assume that suitable reference images are explicitly provided. In practice, suitable references are often not explicitly provided, requiring the system to search for identity-consistent images within personal photo collections. We present AlbumFill, a training-free framework that retrieves identity-consistent references from personal albums for personalized completion. Given an occluded image and a personal album, a vision-language model infers missing semantic cues to guide composed image retrieval, and the retrieved references are used by reference-based completion models. To facilitate this task, we introduce a dataset containing 54K human-centric samples with associated album images. Experiments across multiple baselines demonstrate the difficulty of personalized completion and highlight the importance of identity-consistent reference retrieval. Project Page: https://liagm.github.io/AlbumFill/
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。