Skip to content
프로젝트

mxgmn/TextureSynthesis

GitHub에서 보기

mxgmn/TextureSynthesis has 997 GitHub stars and 56 forks. Star changes are not measured yet. Last checked 2026-11-14 08:25 UTC. Last push 2022-06-01.

이 수치를 측정하는 방법

측정된 스타 증가

in 24h
기록 수집 중
in 7 days
기록 수집 중
in 15 days
기록 수집 중
in 1 month
기록 수집 중

서로 겹치는 기간의 순증가량이며 일별 합계가 아닙니다. 측정값이 없으면 비워 둡니다. 스타는 관심도를 나타내며 품질을 보장하지 않습니다.

소개

Texture synthesis from examples

머신러닝

README.md

Original

The algorithms are:

  1. Full neighbourhood search algorithm of Scott Draves and Alexei Efros + Thomas Leung and Li-Yi Wei + Marc Levoy is probably the simplest texture synthesis algorithm imaginable.
  2. K-coherent neighbourhood search of Michael Ashikhmin and Xin Tong + Jingdan Zhangz + Ligang Liu + Xi Wangz + Baining Guo + Heung-Yeung Shum takes computational burden from the synthesis to the analysis part and therefore is better suited for synthesizing large textures.
  3. Resynthesis algorithm of P. F. Harrison is scale-invariant, fast, supports constraints and practically never produces completely unsatisfactory results.

Note that my implementations are not completely true to the original papers.

Watch a video demonstration of P. F. Harrison's algorithm on YouTube: https://www.youtube.com/watch?v=8sUMBMpZNzk.

How to build

This is a console application that depends only on the standard library. Get .NET Core for Windows, Linux or macOS and run

dotnet run --configuration Release TextureSynthesis.csproj

관련 프로젝트 살펴보기