Innovative Non-parametric Texture Synthesis via Patch Permutations

TL;DR

This paper introduces a non-parametric texture synthesis method that uses patch permutations and optimal transport heuristics to generate plausible, novel textures without large exemplar copying, emphasizing simplicity and global plausibility.

Contribution

The work presents a simple, effective non-parametric texture synthesis algorithm utilizing patch permutations and optimal transport heuristics, achieving plausible textures with minimal copying.

Findings

Synthesized textures contain few or no verbatim copies.

Optimal transport regularization improves permutation quality.

Method compares favorably to statistical convolutional approaches.

Abstract

In this work, we present a non-parametric texture synthesis algorithm capable of producing plausible images without copying large tiles of the exemplar. We focus on a simple synthesis algorithm, where we explore two patch match heuristics; the well known Bidirectional Similarity (BS) measure and a heuristic that finds near permutations using the solution of an entropy regularized optimal transport (OT) problem. Innovative synthesis is achieved with a small patch size, where global plausibility relies on the qualities of the match. For OT, less entropic regularization also meant near permutations and more plausible images. We examine the tile maps of the synthesized images, showing that they are indeed novel superpositions of the input and contain few or no verbatim copies. Synthesis results are compared to a statistical method, namely a random convolutional network. We conclude by remarking simple algorithms using only the input image can synthesize textures decently well and call for more modest approaches in future algorithm design.