Texture Synthesis Through Convolutional Neural Networks and Spectrum Constraints

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.

References in corpus (3)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Return of the Devil in the Details: Delving Deep into Convolutional Nets
• Texture Synthesis Using Convolutional Neural Networks

Cited by in corpus (6)

• On Demand Solid Texture Synthesis Using Deep 3D Networks
• A Generative Model for Texture Synthesis based on Optimal Transport between Feature Distributions
• One-shot Texture Segmentation
• Transposer: Universal Texture Synthesis Using Feature Maps as Transposed Convolution Filter
• Image Inpainting for High-Resolution Textures using CNN Texture Synthesis
• Texture Mixing by Interpolating Deep Statistics via Gaussian Models