Beyond Pixels: Visual Metaphor Transfer via Schema-Driven Agentic Reasoning

TL;DR

This paper introduces a novel multi-agent framework inspired by cognitive theories to enable AI models to transfer abstract visual metaphors between images, significantly improving creative and logical consistency in generated visuals.

Contribution

It proposes a schema-driven, multi-agent system based on Conceptual Blending Theory for autonomous visual metaphor transfer, advancing beyond pixel-level generative models.

Findings

Outperforms state-of-the-art in metaphor consistency and analogy appropriateness

Enhances visual creativity in AI-generated images

Demonstrates effectiveness through extensive experiments and human evaluations

Abstract

A visual metaphor constitutes a high-order form of human creativity, employing cross-domain semantic fusion to transform abstract concepts into impactful visual rhetoric. Despite the remarkable progress of generative AI, existing models remain largely confined to pixel-level instruction alignment and surface-level appearance preservation, failing to capture the underlying abstract logic necessary for genuine metaphorical generation. To bridge this gap, we introduce the task of Visual Metaphor Transfer (VMT), which challenges models to autonomously decouple the "creative essence" from a reference image and re-materialize that abstract logic onto a user-specified target subject. We propose a cognitive-inspired, multi-agent framework that operationalizes Conceptual Blending Theory (CBT) through a novel Schema Grammar ("G"). This structured representation decouples relational invariants from specific visual entities, providing a rigorous foundation for cross-domain logic re-instantiation. Our pipeline executes VMT through a collaborative system of specialized agents: a perception agent that distills the reference into a schema, a transfer agent that maintains generic space invariance to discover apt carriers, a generation agent for high-fidelity synthesis and a hierarchical diagnostic agent that mimics a professional critic, performing closed-loop backtracking to identify and rectify errors across abstract logic, component selection, and prompt encoding. Extensive experiments and human evaluations demonstrate that our method significantly outperforms SOTA baselines in metaphor consistency, analogy appropriateness, and visual creativity, paving the way for automated high-impact creative applications in advertising and media. Source code will be made publicly available.