Collascope: Supporting Serendipitous Asset Exploration for Collage-Based Storytelling

2026-08-02

AI Summary

This work addresses the limitations of existing collage tools, which rely on keyword-based or holistic image retrieval and struggle to support serendipitous discovery and creative reinterpretation driven by narrative intent. To overcome this, we propose Collascope, an interactive system that explicitly encodes storytelling intent through manipulable element groupings and introduces an attribute-aware visual retrieval approach. Rather than matching overall image similarity, our method projects queries along specific visual dimensions—such as conceptual content or cropping style—thereby simultaneously expanding both compositional and semantic exploration spaces. The system integrates dimension-specific projections, scene-component organization, and interactive grouping mechanisms. A user study (N=12) demonstrates that Collascope effectively leverages serendipitous retrieval results and material gaps to flexibly adjust narrative direction, shift tonal emphasis, and enrich composition, significantly enhancing creative depth and flexibility.

Abstract

Collage-based storytelling requires visual elements that support emerging narratives and inspire creative reinterpretation. Existing tools, however, rely largely on keyword- and image-based retrieval, offering limited support for serendipitous exploration beyond existing assets. We introduce Collascope, an interactive system that helps creators (1) concretize story intent with interactive element groups, (2) expand the exploration space based on concepts or cutouts towards conceptual and visual dimensions, and (3) develop grounded, traceable ideas in parallel with collage composition. Collascope's attribute-aware visual retrieval method, instantiated with collage-relevant visual dimensions, enables creators to retrieve cutouts through dimension-specific visual projections rather than holistic similarity. In a within-subject study (N=12) against a conventional search baseline, our participants used unexpected results and even gaps in the asset collection to redirect narratives, shift tone, and enrich compositions. Scene Parts helped organize exploration into manageable subtasks, while participants used association in distinct ways depending on whether exploration was guided by a clear goal, an evolving story, or visual intuition.

Problem

• collage-based storytelling
• serendipitous exploration
• visual asset retrieval
• creative reinterpretation
• narrative emergence

Innovation

• serendipitous exploration
• attribute-aware retrieval
• collage-based storytelling
• visual dimensions
• interactive element groups