Real-time texture synthesis by patch-based sampling
- 30 June 2001
- journal article
- research article
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Graphics
- Vol. 20 (3), 127-150
- https://doi.org/10.1145/501786.501787
Abstract
We present an algorithm for synthesizing textures from an input sample. This patch-based sampling algorithm is fast and it makes high-quality texture synthesis a real-time process. For generating textures of the same size and comparable quality, patch-based sampling is orders of magnitude faster than existing algorithms. The patch-based sampling algorithm works well for a wide variety of textures ranging from regular to stochastic. By sampling patches according to a nonparametric estimation of the local conditional MRF density function, we avoid mismatching features across patch boundaries. We also experimented with documented cases for which pixel-based nonparametric sampling algorithms cease to be effective but our algorithm continues to work well.This publication has 23 references indexed in Scilit:
- Texture mixing and texture movie synthesis using statistical learningIEEE Transactions on Visualization and Computer Graphics, 2001
- Texture and Shape Synthesis on SurfacesPublished by Springer Science and Business Media LLC ,2001
- Exploring texture ensembles by efficient Markov chain Monte Carlo-Toward a "trichromacy" theory of textureIEEE Transactions on Pattern Analysis and Machine Intelligence, 2000
- An optimal algorithm for approximate nearest neighbor searching in fixed dimensionsJournal of the ACM, 1998
- Minimax Entropy Principle and Its Application to Texture ModelingNeural Computation, 1997
- A simple algorithm for nearest neighbor search in high dimensionsIeee Transactions On Pattern Analysis and Machine Intelligence, 1997
- An evaluation of stochastic models for analysis and synthesis of gray-scale texturePattern Recognition Letters, 1994
- Computer rendering of stochastic modelsCommunications of the ACM, 1982
- Finding structure in Co-occurrence matrices for texture analysisComputer Graphics and Image Processing, 1980
- An Algorithm for Finding Best Matches in Logarithmic Expected TimeACM Transactions on Mathematical Software, 1977