Weaving Visual Narratives: Agentic Image Bundle Composition Beyond Atomic Visual Matching

• URL: http://arxiv.org/abs/2608.28695v1
• Date: Thu, 27 Aug 2026 07:50:11 GMT
• Title: Weaving Visual Narratives: Agentic Image Bundle Composition Beyond Atomic Visual Matching
• Abstract summary: We introduce **Image Bundle Composition (IBC)**, a novel paradigm that shifts the objective from ranking individual images to dynamically composing cohesive image bundles.<n>IBC presents a severe explosion challenge and demands modeling non-decomposable joint relevance.<n>By employing a Large Language Model to adaptively search for missing relational roles and utilizing a Vision-Language Model for whole-bundle verification, BundleWeaver effectively navigates the space.
• Score: 39.681024131939814
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Image retrieval has traditionally been formulated as a point-wise matching problem, where each candidate image is scored in isolation. However, this atomic paradigm fails to capture the complexity of human search intent within personal photo collections, where users often seek compact visual stories bound by structural relations rather than isolated snapshots. To address this limitation, we introduce **Image Bundle Composition (IBC)**, a novel paradigm that shifts the objective from ranking individual images to dynamically composing cohesive image bundles from a massive, unstructured photo pool. Since target bundles are not predefined, IBC presents a severe combinatorial explosion challenge and demands modeling non-decomposable joint relevance. To establish this paradigm, we construct **IBCBench**, the first IBC benchmark dataset containing 109,467 images and 667 verified queries, built via a semi-automated verification pipeline. Furthermore, we propose **BundleWeaver**, an agentic framework that reformulates IBC as query-conditioned incremental hyperedge discovery. By employing a Large Language Model to adaptively search for missing relational roles and utilizing a Vision-Language Model for whole-bundle verification, BundleWeaver effectively navigates the combinatorial space. Extensive experiments demonstrate that while state-of-the-art embedding models and static decompose-and-rerank paradigms suffer from relational blindness, BundleWeaver achieves substantial performance gains, highlighting the necessity of shifting from atomic scoring to dynamic relational composition. Our dataset and code are available.

Related papers

• Rank-Consistent Set Reasoning for Co-Salient Object Detection [0.548014499873554]
  Co-salient object detection (Co-SOD) requires a model to find foreground regions that are salient in individual images and supported by the image group.<n>We present emphRank-Consistent Set Reasoning (RCSR), a supervised dense-prediction framework that models a group as an unordered set.
  arXiv  Detail & Related papers  (2026-09-12T04:34:48Z)
• Beyond Semantic Search: Towards Referential Anchoring in Composed Image Retrieval [56.72697928941446]
  Composed Image Retrieval (CIR) has demonstrated significant potential by enabling flexible multimodal queries that combine a reference image and modification text.<n>We propose Object-Anchored Composed Image Retrieval (OACIR), a novel fine-grained retrieval task that mandates strict instance-level consistency.
  arXiv  Detail & Related papers  (2026-04-07T03:43:01Z)
• 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)
• DeepImageSearch: Benchmarking Multimodal Agents for Context-Aware Image Retrieval in Visual Histories [52.57197752244638]
  We introduce DeepImageSearch, a novel agentic paradigm that reformulates image retrieval as an autonomous exploration task.<n>Models must plan and perform multi-step reasoning over raw visual histories to locate targets based on implicit contextual cues.<n>We construct DISBench, a challenging benchmark built on interconnected visual data.
  arXiv  Detail & Related papers  (2026-02-11T12:51:10Z)
• Composed Object Retrieval: Object-level Retrieval via Composed Expressions [71.47650333199628]
  Composed Object Retrieval (COR) is a brand-new task that goes beyond image-level retrieval to achieve object-level precision.<n>We construct COR127K, the first large-scale COR benchmark that contains 127,166 retrieval triplets with various semantic transformations in 408 categories.<n>We also present CORE, a unified end-to-end model that integrates reference region encoding, adaptive visual-textual interaction, and region-level contrastive learning.
  arXiv  Detail & Related papers  (2025-08-06T13:11:40Z)
• Cross-modal RAG: Sub-dimensional Text-to-Image Retrieval-Augmented Generation [16.411920699543774]
  Cross-modal RAG is a novel framework that decomposes both queries and images into sub-dimensional components.<n>Our method introduces a hybrid retrieval strategy - combining a sub-dimensional sparse retriever with a dense retriever.<n>Experiments on MS-COCO, Flickr30K, WikiArt, CUB, and ImageNet-LT demonstrate that Cross-modal RAG significantly outperforms existing baselines in the retrieval.
  arXiv  Detail & Related papers  (2025-05-28T04:09:49Z)
• CONDA: Condensed Deep Association Learning for Co-Salient Object Detection [136.30039346735833]
  This paper proposes a deep association learning strategy that deploys deep networks on raw associations to transform them into deep association features. Experimental results in three benchmark datasets demonstrate the remarkable effectiveness of our proposed method with various training settings.
  arXiv  Detail & Related papers  (2024-09-02T08:01:32Z)
• CoADNet: Collaborative Aggregation-and-Distribution Networks for Co-Salient Object Detection [91.91911418421086]
  Co-Salient Object Detection (CoSOD) aims at discovering salient objects that repeatedly appear in a given query group containing two or more relevant images. One challenging issue is how to effectively capture co-saliency cues by modeling and exploiting inter-image relationships. We present an end-to-end collaborative aggregation-and-distribution network (CoADNet) to capture both salient and repetitive visual patterns from multiple images.
  arXiv  Detail & Related papers  (2020-11-10T04:28:11Z)

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.