TexTile: A Differentiable Metric for Texture Tileability

TL;DR

It is demonstrated that TexTile can be plugged into different state-of-the-art texture synthesis methods, in-cluding diffusion-based strategies, and generate tileable textures while keeping or even improving the overall texture quality.

Abstract

We introduce TexTile, a novel differentiable metric to quantify the degree upon which a texture image can be concatenated 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 texture. In contrast, our TexTile metric effectively evaluates the tileable properties of a texture, opening the door to more informed 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, semantics, 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 augmentation 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, including diffusion-based strategies, and generate tileable textures 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.

Figures (10)

• Figure 1: Existing perceptual metrics, commonly used to evaluate texture synthesis algorithms, typically fail to account for tileability. Such weakness is depicted in this figure where, for each column, we show tiled versions of textures with (top) and without (bottom) tiling artifacts. For each column, we highlight using saturated color dots the preferred image (i.e., higher score) according to different metrics. It can be seen that there is no correlation across existing methods (i.e., saturated dots distributed over top and bottom rows), while our method TexTile consistently prefers seamless tiled textures (i.e., saturated green dots on the bottom for all columns).
• Figure 2: Our model takes as input a texture image $\text{I}$, which we tile to form $\text{I}_{\text{tiled}}$, and returns an estimation of its tileability. This metric can be used as a loss function $\mathcal{L}_{\text{TexTile}}$ to allow synthesis algorithms to generate tileable textures. Our model, $\mathcal{M}$ architecture is comprised of ConvNext liu2022convnet and residual self-attention blocks.
• Figure 3: From a tileable texture (left), our data augmentation can generate tileable (top row) and non-tileable (bottom) variations.
• Figure 4: Influence on the neural architecture type and size on its quantitative performance (Cross-entropy error on the validation dataset). Convolutional architectures are marked with ${ \blacksquare }$, attention-based models with $\mathbin{\vcenter{\hbox{$\bullet$}}}$, and our versions of convolutional networks with embedded attention with ${ \footnotesize \mathord{\text{✚}} }$.
• Figure 5: On top, textures samples (tiled $2\times2$) with increasing predicted tileability. Below them, model saliency maps and TexTile values.