SYNTHIA: Novel Concept Design with Affordance Composition

TL;DR

SYNTHIA is a novel framework that uses hierarchical ontologies and curriculum learning to generate functionally coherent, visually novel concepts with desired affordances, advancing AI-driven design capabilities.

Contribution

It introduces a hierarchical ontology and curriculum learning scheme for T2I models to improve affordance-based concept synthesis with enhanced coherence and novelty.

Findings

Outperforms state-of-the-art models in novelty and coherence

Achieves 25.1% gain in novelty and 14.7% in coherence

Demonstrates effective affordance composition in generated designs

Abstract

Text-to-image (T2I) models enable rapid concept design, making them widely used in AI-driven design. While recent studies focus on generating semantic and stylistic variations of given design concepts, functional coherence--the integration of multiple affordances into a single coherent concept--remains largely overlooked. In this paper, we introduce SYNTHIA, a framework for generating novel, functionally coherent designs based on desired affordances. Our approach leverages a hierarchical concept ontology that decomposes concepts into parts and affordances, serving as a crucial building block for functionally coherent design. We also develop a curriculum learning scheme based on our ontology that contrastively fine-tunes T2I models to progressively learn affordance composition while maintaining visual novelty. To elaborate, we (i) gradually increase affordance distance, guiding models from basic concept-affordance association to complex affordance compositions that integrate parts of distinct affordances into a single, coherent form, and (ii) enforce visual novelty by employing contrastive objectives to push learned representations away from existing concepts. Experimental results show that SYNTHIA outperforms state-of-the-art T2I models, demonstrating absolute gains of 25.1% and 14.7% for novelty and functional coherence in human evaluation, respectively.