Texture Mixer: A Network for Controllable Synthesis and Interpolation of Texture
Authors:
- 1 June 2019
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 12156-12165
Abstract
This paper addresses the problem of interpolating visual textures. We formulate this problem by requiring (1) by-example controllability and (2) realistic and smooth interpolation among an arbitrary number of texture samples. To solve it we propose a neural network trained simultaneously on a reconstruction task and a generation task, which can project texture examples onto a latent space where they can be linearly interpolated and projected back onto the image domain, thus ensuring both intuitive control and realistic results. We show our method outperforms a number of baselines according to a comprehensive suite of metrics as well as a user study. We further show several applications based on our technique, which include texture brush, texture dissolve, and animal hybridization.Keywords
All Related Versions
This publication has 25 references indexed in Scilit:
- Self Tuning Texture OptimizationComputer Graphics Forum, 2015
- Synthesis of Complex Image Appearance from Limited ExemplarsACM Transactions on Graphics, 2015
- Image meldingACM Transactions on Graphics, 2012
- PatchMatchACM Transactions on Graphics, 2009
- Texture optimization for example-based synthesisACM Transactions on Graphics, 2005
- Texture design using a simplicial complex of morphable textures2005
- Poisson image editingACM Transactions on Graphics, 2003
- Graphcut texturesACM Transactions on Graphics, 2003
- Image quilting for texture synthesis and transfer2001
- Fast texture synthesis using tree-structured vector quantization2000