Diversified Texture Synthesis with Feed-Forward Networks

Citations Over TimeTop 10% of 2017 papers

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.

Related Papers

• → Machine Learning: Discriminative and Generative(2012)165 cited
• On Separability of Loss Functions, and Revisiting Discriminative Vs Generative Models(2017)
• → Generative and Discriminative Text Classification with Recurrent Neural\n Networks(2017)110 cited
• → Generative and Discriminative Text Classification with Recurrent Neural Networks(2017)108 cited
• → Discriminative Models Can Still Outperform Generative Models in Aspect Based Sentiment Analysis(2022)