Pattern Analogies: Learning to Perform Programmatic Image Edits by Analogy

TL;DR

This paper presents a novel method for programmatic pattern image editing using pattern analogies and a specialized generative model, enabling intuitive and accurate edits that generalize across styles.

Contribution

Introduces SplitWeave, a domain-specific language, and TriFuser, a Latent Diffusion Model, to facilitate learning-based, structure-aware pattern edits from synthetic training data.

Findings

Method accurately performs demonstrated pattern edits.

Model generalizes well to unseen pattern styles.

Synthetic dataset improves training effectiveness.

Abstract

Pattern images are everywhere in the digital and physical worlds, and tools to edit them are valuable. But editing pattern images is tricky: desired edits are often programmatic: structure-aware edits that alter the underlying program which generates the pattern. One could attempt to infer this underlying program, but current methods for doing so struggle with complex images and produce unorganized programs that make editing tedious. In this work, we introduce a novel approach to perform programmatic edits on pattern images. By using a pattern analogy -- a pair of simple patterns to demonstrate the intended edit -- and a learning-based generative model to execute these edits, our method allows users to intuitively edit patterns. To enable this paradigm, we introduce SplitWeave, a domain-specific language that, combined with a framework for sampling synthetic pattern analogies, enables the creation of a large, high-quality synthetic training dataset. We also present TriFuser, a Latent Diffusion Model (LDM) designed to overcome critical issues that arise when naively deploying LDMs to this task. Extensive experiments on real-world, artist-sourced patterns reveals that our method faithfully performs the demonstrated edit while also generalizing to related pattern styles beyond its training distribution.