AlbumFill: Album-Guided Reasoning and Retrieval for Personalized Image Completion

• URL: http://arxiv.org/abs/2605.02892v1
• Date: Mon, 04 May 2026 17:59:59 GMT
• Title: AlbumFill: Album-Guided Reasoning and Retrieval for Personalized Image Completion
• Abstract summary: AlbumFill is a training-free framework that retrieves identity-consistent references from personal albums for personalized completion.<n>Given an occluded image and a personal album, a vision-language model infers missing semantic cues to guide composed image retrieval.
• Score: 37.657996066098484
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: 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/

Related papers

• WithEveryone: Unified Planning and Identity Grounding for Group Image Generation [60.528070962852716]
  We introduce WithEveryone, a unified framework for generating group images up to ten reference identities.<n>WithEveryone injects each selected identity as an addressed token, predicts a structured identity--plan, and renders the plan as a visual condition.<n>It achieves the highest target-context identity similarity, improving face similarity from 0.462 for GPT-Image-2 to 0.499, while reducing copy-paste artifacts from 0.169 to 0.055.
  arXiv  Detail & Related papers  (2026-08-20T17:59:53Z)
• PhotoBench: Beyond Visual Matching Towards Personalized Intent-Driven Photo Retrieval [29.907367363360652]
  PhotoBench is the first benchmark constructed from authentic, personal albums.<n>It is designed to shift the paradigm from visual matching to personalized multi-source intent-driven reasoning.
  arXiv  Detail & Related papers  (2026-03-02T06:02:40Z)
• Reverse Personalization [48.09783075634403]
  We analyze the identity generation process and introduce a reverse personalization framework for face anonymization.<n>Unlike prior anonymization methods, which lack control over facial attributes, our framework supports attribute-controllable anonymization.
  arXiv  Detail & Related papers  (2025-12-28T16:06:55Z)
• Finer-Personalization Rank: Fine-Grained Retrieval Examines Identity Preservation for Personalized Generation [34.915564029238105]
  Finer-Personalization Rank is an evaluation protocol tailored to identity preservation.<n>It treats each generated image as a query against an identity-labeled gallery consisting of visually similar real images.<n>Retrieval metrics measure performance, where higher scores indicate that identity-specific details are preserved.
  arXiv  Detail & Related papers  (2025-12-22T04:53:40Z)
• CompleteMe: Reference-based Human Image Completion [52.93963237043788]
  We propose CompleteMe, a novel reference-based human image completion framework.<n>CompleteMe employs a dual U-Net architecture combined with a Region-focused Attention (RFA) Block.<n>Our proposed method achieves superior visual quality and semantic consistency compared to existing techniques.
  arXiv  Detail & Related papers  (2025-04-28T17:59:56Z)
• ID-Cloak: Crafting Identity-Specific Cloaks Against Personalized Text-to-Image Generation [54.14901999875917]
  We investigate the creation of identity-specific cloaks that safeguard all images belong to a specific identity.<n>We craft identity-specific cloaks with the proposed novel objective that encourages the cloak to guide the model away from its normal output.<n>Our method, along with the proposed identity-specific cloak setting, marks a notable advance in realistic privacy protection.
  arXiv  Detail & Related papers  (2025-02-12T03:52:36Z)
• FaceMe: Robust Blind Face Restoration with Personal Identification [27.295878867436688]
  We propose a personalized face restoration method, FaceMe, based on a diffusion model.<n>Given a single or a few reference images, we use an identity encoder to extract identity-related features, which serve as prompts to guide the diffusion model in restoring high-quality facial images.<n> Experimental results demonstrate that our FaceMe can restore high-quality facial images while maintaining identity consistency, achieving excellent performance and robustness.
  arXiv  Detail & Related papers  (2025-01-09T11:52:54Z)
• Resolving Multi-Condition Confusion for Finetuning-Free Personalized Image Generation [10.416673784744281]
  We propose a weighted-merge method to merge multiple reference image features into corresponding objects.<n>Our method achieves superior performance to the state-of-the-arts on the Concept101 dataset and DreamBooth dataset of multi-object personalized image generation.
  arXiv  Detail & Related papers  (2024-09-26T15:04:13Z)
• Measuring Style Similarity in Diffusion Models [118.22433042873136]
  We present a framework for understanding and extracting style descriptors from images. Our framework comprises a new dataset curated using the insight that style is a subjective property of an image. We also propose a method to extract style attribute descriptors that can be used to style of a generated image to the images used in the training dataset of a text-to-image model.
  arXiv  Detail & Related papers  (2024-04-01T17:58:30Z)
• Personalized Image Semantic Segmentation [58.980245748434]
  We generate more accurate segmentation results on unlabeled personalized images by investigating the data's personalized traits. We propose a baseline method that incorporates the inter-image context when segmenting certain images. The code and the PIS dataset will be made publicly available.
  arXiv  Detail & Related papers  (2021-07-24T04:03:11Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.