$I^2G$: Generating Instructional Illustrations via Text-Conditioned Diffusion

TL;DR

This paper introduces $I^2G$, a framework that converts procedural instructions into visual illustrations using text-conditioned diffusion, enhancing the communication of complex physical and spatial instructions.

Contribution

It presents a novel language-driven approach with a constituency parser-based encoding, discourse coherence modeling, and a new evaluation protocol for procedural language-to-image generation.

Findings

Outperforms existing methods on three instructional datasets

Accurately reflects linguistic content and sequence in generated visuals

Improves grounding of procedural language in visual content

Abstract

The effective communication of procedural knowledge remains a significant challenge in natural language processing (NLP), as purely textual instructions often fail to convey complex physical actions and spatial relationships. We address this limitation by proposing a language-driven framework that translates procedural text into coherent visual instructions. Our approach models the linguistic structure of instructional content by decomposing it into goal statements and sequential steps, then conditioning visual generation on these linguistic elements. We introduce three key innovations: (1) a constituency parser-based text encoding mechanism that preserves semantic completeness even with lengthy instructions, (2) a pairwise discourse coherence model that maintains consistency across instruction sequences, and (3) a novel evaluation protocol specifically designed for procedural language-to-image alignment. Our experiments across three instructional datasets (HTStep, CaptainCook4D, and WikiAll) demonstrate that our method significantly outperforms existing baselines in generating visuals that accurately reflect the linguistic content and sequential nature of instructions. This work contributes to the growing body of research on grounding procedural language in visual content, with applications spanning education, task guidance, and multimodal language understanding.