Texture Synthesis Through Convolutional Neural Networks and Spectrum Constraints

2016/05/04 by Gang Liu, Yann Gousseau, Liu, Gang +3 · 1 citation
Computer Science · #Advanced Neural Network Applications #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Generative Adversarial Networks and Image Synthesis #Medical Image Segmentation Techniques

paper · pdf · doi:10.48550/arxiv.1605.01141

openalex publication_date 2016/05/04 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

This paper presents a significant improvement for the synthesis of texture images using convolutional neural networks (CNNs), making use of constraints on the Fourier spectrum of the results. More precisely, the texture synthesis is regarded as a constrained optimization problem, with constraints conditioning both the Fourier spectrum and statistical features learned by CNNs. In contrast with existing methods, the presented method inherits from previous CNN approaches the ability to depict local structures and fine scale details, and at the same time yields coherent large scale structures, even in the case of quasi-periodic images. This is done at no extra computational cost. Synthesis experiments on various images show a clear improvement compared to a recent state-of-the art method relying on CNN constraints only.

Citations

• Very Deep Convolutional Networks for Large-Scale Image Recognition

Cited by

• Image Inpainting for High-Resolution Textures using CNN Texture Synthesis

Related

• High resolution neural texture synthesis with long range constraints
• Texture Synthesis Using Convolutional Neural Networks
• Texture Synthesis Using Shallow Convolutional Networks with Random Filters
• Transposer: Universal Texture Synthesis Using Feature Maps as Transposed Convolution Filter
• Incorporating long-range consistency in CNN-based texture generation