CVPR2025

Pattern Analogies: Learning to Perform Programmatic Image Edits by Analogy

Aditya Ganeshan, Thibault Groueix, Paul Guerrero, Radomír Mech, Matthew Fisher, Daniel Ritchie

Abstract

Figure 1. Our system performs programmatic edits on pattern images without inferring their underlying programs. (Left) Desired edits, expressed with a pair of patterns (A, A ), are executed on a target pattern B by a generative model to produce B . (Right) Parametric changes A → A enabled by our domain-specific pattern language induce corresponding changes to the more complex pattern B.