Diversified Texture Synthesis with Feed-forward Networks
1Univerisity of California, Merced                          2Adobe Research

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.


Single texture diverse synthesis

Texture transition (interpolation)

Style transition (interpolation)

    author = {Li, Yijun and Fang, Chen and Yang, Jimei and Wang, Zhaowen and Lu, Xin and Yang, Ming-Hsuan},
    title = {Diversified Texture Synthesis with Feed-forward Networks},
    booktitle = {IEEE Conference on Computer Vision and Pattern Recognition},
    year = {2017}

This work was performed during a summer internship at Adobe Research.