Researches on wxs.ca

Mon, 01 Jan 0001 00:00:00 +0000

High-Resolution Multi-Scale Neural Texture Synthesis

Supplemental Images (click to see full-size)

Source Our result Gatys et al.

High-Resolution Multi-Scale Neural Texture Synthesis

Mon, 01 Jan 0001 00:00:00 +0000

TL;DR If you’re doing neural texture synthesis, use a multi-scale Gaussian pyramid representation and everything will look better!

Demonstration of the texture synthesis algorithm from a high-resolution source (source credit Halei Laihaweadu)

To appear at SIGGRAPH Asia 2017: Read the paper. Get the code.

Overview

The Neural Algorithm of Artistic Style (Gatys, Ecker and Bethge 2015) was a groundbreaking paper, the “Gram matrix” of feature activations is used to represent a texture, basically a covariance matrix of features “How often does the ‘stripy’ feature co-occur with the ‘green’ feature”. This work triggered an explosion of research into using convolutional neural-network based representations of textures and images to synthesize new ones.

Interactive CPPNs in GLSL

Mon, 01 Jan 0001 00:00:00 +0000

TL;DR Compositional Pattern Producing Networks (CPPNs) are learned functions mapping x,y coordinates to r,g,b colours, much like fragment shaders in the graphics pipeline. So, they can be easily implemented in GLSL and integrated into existing media arts pipelines.

Authors: Xavier Snelgrove and Matthew Tesfaldet

Poster at the 2018 NeurIPS Workshop on Machine Learning for Creativity and Design:

Try interactive demos in your browser

GLSL CPPNs can run in the browser using WebGL. Try a few examples here, hosted on ShaderToy.