A Common Framework for Interactive Texture Transfer


Fig.1 Representative results generated using our interactive structure-guided texture transfer framework. The stylized images are synthesized with the guidance of corresponding user-specified semantic maps. The proposed common framework is capable of multiple challenging user-controlled texture transfer tasks: (a) turning doodles into artworks, (b) editing decorative patterns, (c) generating texts in special effect, (d) controlling effect distribution in text images, (e) swapping textures.


In this paper, we present a general-purpose solution to interactive texture transfer problems that better preserves both local structure and visual richness. It is challenging due to the diversity of tasks and the simplicity of required user guidance. The core idea of our common framework is to use multiple custom channels to dynamically guide the synthesis process. For interactivity, users can control the spatial distribution of stylized textures via semantic channels. The structure guidance, acquired by two stages of automatic extraction and propagation of structure information, provides a prior for initialization and preserves the salient structure by searching the nearest neighbor fields (NNF) with structure coherence. Meanwhile, texture coherence is also exploited to maintain similar style with the source image. In addition, we leverage an improved PatchMatch with extended NNF and matrix operations to obtain transformable source patches with richer geometric information at high speed. We demonstrate the effectiveness and superiority of our method on a variety of scenes through extensive comparisons with state-of-the-art algorithms.

Fig. 2. The pipeline of our framework.


  • Paper: pdf
  • Supplementary Material: pdf
  • Poster: pdf
  • Code: github
  • Experimental Results

    Semantic Texture Transfer


    @inproceedings{men2018common,   title={A Common Framework for Interactive Texture Transfer},   author={Men, Yifang and Lian, Zhouhui and Tang, Yingmin and Xiao, Jianguo},   booktitle={Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition},   pages={6353--6362},   year={2018} }

    => Back to main project page <=