Diversified Texture Synthesis with Feed-forward Networks

Abstract

Recent progresses on deep discriminative and generative modeling have shown promising results on texture synthesis. However, existing feed-forward based methods trade off generality for efficiency, which suffer from many issues, such as shortage of generality (i.e., build one network per texture), lack of diversity (i.e., always produce visually identical output) and suboptimality (i.e., generate less satisfying visual effects). In this work, we focus on solving these issues for improved texture synthesis. We propose a deep generative feed-forward network which enables efficient synthesis of multiple textures within one single network and meaningful interpolation between them. Meanwhile, a suite of important techniques are introduced to achieve better convergence and diversity. With extensive experiments, we demonstrate the effectiveness of the proposed model and techniques for synthesizing a large number of textures and show its applications with the stylization.

accepted by CVPR2017

References in corpus (7)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Instance Normalization: The Missing Ingredient for Fast Stylization
• Deep Generative Image Models using a Laplacian Pyramid of Adversarial Networks
• Improved Techniques for Training GANs
• Texture Networks: Feed-forward Synthesis of Textures and Stylized Images
• Texture Synthesis Using Convolutional Neural Networks
• Preserving Color in Neural Artistic Style Transfer

Cited by in corpus (13)

• ZM-Net: Real-time Zero-shot Image Manipulation Network
• On Demand Solid Texture Synthesis Using Deep 3D Networks
• TextureGAN: Controlling Deep Image Synthesis with Texture Patches
• Meta Networks for Neural Style Transfer
• Towards Metamerism via Foveated Style Transfer
• Generating Neural Networks with Neural Networks
• Language-Driven Image Style Transfer
• GUN: Gradual Upsampling Network for Single Image Super-Resolution
• Parameter-Free Style Projection for Arbitrary Style Transfer
• Neural Stereoscopic Image Style Transfer
• Learning to Caricature via Semantic Shape Transform
• A Generative Model for Sampling High-Performance and Diverse Weights for Neural Networks
• Optimal Textures: Fast and Robust Texture Synthesis and Style Transfer through Optimal Transport