Text-to-Image Generation for Abstract Concepts

TL;DR

This paper introduces TIAC, a novel framework that enhances text-to-image models to better visualize abstract concepts by integrating intent, physical objects, and form patterns, validated through human and metric evaluations.

Contribution

The paper proposes a new framework for T2I generation that effectively visualizes abstract concepts by combining semantic clarification, object retrieval, and form pattern integration.

Findings

TIAC outperforms existing models in expressing abstract concepts.

Human assessments and the concept score metric confirm the framework's effectiveness.

The approach successfully bridges the gap between abstract semantics and visual representation.

Abstract

Recent years have witnessed the substantial progress of large-scale models across various domains, such as natural language processing and computer vision, facilitating the expression of concrete concepts. Unlike concrete concepts that are usually directly associated with physical objects, expressing abstract concepts through natural language requires considerable effort, which results from their intricate semantics and connotations. An alternative approach is to leverage images to convey rich visual information as a supplement. Nevertheless, existing Text-to-Image (T2I) models are primarily trained on concrete physical objects and tend to fail to visualize abstract concepts. Inspired by the three-layer artwork theory that identifies critical factors, intent, object and form during artistic creation, we propose a framework of Text-to-Image generation for Abstract Concepts (TIAC). The abstract concept is clarified into a clear intent with a detailed definition to avoid ambiguity. LLMs then transform it into semantic-related physical objects, and the concept-dependent form is retrieved from an LLM-extracted form pattern set. Information from these three aspects will be integrated to generate prompts for T2I models via LLM. Evaluation results from human assessments and our newly designed metric concept score demonstrate the effectiveness of our framework in creating images that can sufficiently express abstract concepts.