TexTile: A Differentiable Metric for Texture Tileability

Carlos Rodríguez-Pardo, Dan Casas, Elena Garcés, Jorge López-Moreno,
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024


We introduce TexTile, a novel differentiable metric to quantify the degree upon which a texture image can be con- catenated with itself without introducing repeating artifacts (i.e., the tileability). Existing methods for tileable texture synthesis focus on general texture quality, but lack explicit analysis of the intrinsic repeatability properties of a tex- ture. In contrast, our TexTile metric effectively evaluates the tileable properties of a texture, opening the door to more in- formed synthesis and analysis of tileable textures. Under the hood, TexTile is formulated as a binary classifier carefully built from a large dataset of textures of different styles, se- mantics, regularities, and human annotations. Key to our method is a set of architectural modifications to baseline pre-train image classifiers to overcome their shortcomings at measuring tileability, along with a custom data augmen- tation and training regime aimed at increasing robustness and accuracy. We demonstrate that TexTile can be plugged into different state-of-the-art texture synthesis methods, in- cluding diffusion-based strategies, and generate tileable tex- tures while keeping or even improving the overall texture quality. Furthermore, we show that TexTile can objectively evaluate any tileable texture synthesis method, whereas the current mix of existing metrics produces uncorrelated scores which heavily hinders progress in the field.


    author = {Rodriguez-Pardo, Carlos and Casas, Dan and Garces, Elena and Lopez-Moreno, Jorge},
    title = {TexTile: A Differentiable Metric for Texture Tileability},
    booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, 
    year = {2024}



Carlos Rodríguez-Pardo – carlos.rodriguezpardo.jimenez@gmail.com