English

Generalized Rectifier Wavelet Covariance Models For Texture Synthesis

Computer Vision and Pattern Recognition 2022-03-16 v1 Machine Learning Image and Video Processing Signal Processing Machine Learning

Abstract

State-of-the-art maximum entropy models for texture synthesis are built from statistics relying on image representations defined by convolutional neural networks (CNN). Such representations capture rich structures in texture images, outperforming wavelet-based representations in this regard. However, conversely to neural networks, wavelets offer meaningful representations, as they are known to detect structures at multiple scales (e.g. edges) in images. In this work, we propose a family of statistics built upon non-linear wavelet based representations, that can be viewed as a particular instance of a one-layer CNN, using a generalized rectifier non-linearity. These statistics significantly improve the visual quality of previous classical wavelet-based models, and allow one to produce syntheses of similar quality to state-of-the-art models, on both gray-scale and color textures.

Keywords

Cite

@article{arxiv.2203.07902,
  title  = {Generalized Rectifier Wavelet Covariance Models For Texture Synthesis},
  author = {Antoine Brochard and Sixin Zhang and Stéphane Mallat},
  journal= {arXiv preprint arXiv:2203.07902},
  year   = {2022}
}

Comments

To be published as a conference paper at the International Conference on Learning Representations (ICLR) 2022

R2 v1 2026-06-24T10:13:59.959Z