Pattern Analogies: Learning to Perform Programmatic Image Edits by Analogy

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Ganeshan, Aditya, Groueix, Thibault, Guerrero, Paul, Měch, Radomír, Fisher, Matthew, Ritchie, Daniel
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866912310128279552
author Ganeshan, Aditya
Groueix, Thibault
Guerrero, Paul
Měch, Radomír
Fisher, Matthew
Ritchie, Daniel
author_facet Ganeshan, Aditya
Groueix, Thibault
Guerrero, Paul
Měch, Radomír
Fisher, Matthew
Ritchie, Daniel
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2412_12463
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Pattern Analogies: Learning to Perform Programmatic Image Edits by Analogy
Ganeshan, Aditya
Groueix, Thibault
Guerrero, Paul
Měch, Radomír
Fisher, Matthew
Ritchie, Daniel
Computer Vision and Pattern Recognition
Artificial Intelligence
Graphics
Human-Computer Interaction
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.
title Pattern Analogies: Learning to Perform Programmatic Image Edits by Analogy
topic Computer Vision and Pattern Recognition
Artificial Intelligence
Graphics
Human-Computer Interaction
url https://arxiv.org/abs/2412.12463