Abstract

In this work, we propose a system that covers the complete workflow for achieving controlled authoring and editing of textures that present distinctive local characteristics. These include various effects that change the surface appearance of materials, such as stains, tears, holes, abrasions, discoloration, and more. Such alterations are ubiquitous in nature, and including them in the synthesis process is crucial for generating realistic textures. We introduce a novel approach for creating textures with such blemishes, adopting a learning-based approach that leverages unlabeled examples. Our approach does not require manual annotations by the user; instead, it detects the appearance-altering features through unsupervised anomaly detection. The various textural features are then automatically clustered into semantically coherent groups, which are used to guide the conditional generation of images. Our pipeline as a whole goes from a small image collection to a versatile generative model that enables the user to interactively create and paint features on textures of arbitrary size. Notably, the algorithms we introduce for diffusion-based editing and infinite stationary texture generation are generic and should prove useful in other contexts as well.

Publication

Example-Based Feature Painting on Textures.
Andrei-Timotei Ardelean, Tim Weyrich.
ACM Transactions on Graphics (Proc. SIGGRAPH Asia), 10 pages, 2025.

<asset-thumbnails>

Source Code

Here we provide the source code of the software underlying the above publications. The software is provided as-is, and in its current version mainly for research purposes. Installation and licensing details can be found inside each software package.

⛶

An H3 Heading, just for good measure

A user documentation is currently under preparation.

We plan to further refine the software to make it more accessible to end-users in memory institutions. Please check in later again, or contact us at parchment@cs.ucl.ac.uk if you would like to be notified of any updates.

Source code downloads:

And here’s a bullet list…

• with text that is so long it wraps around like text that is so long it wraps around like text that is so long it wraps around
• and two more
• items

and an enumeration, which looks so ugly we should avoid using it:

1. first
2. second
3. third

An here is some a monospace code block:

@inproceedings{ardelean2025quantized,
  author = {Ardelean, Andrei-Timotei and R{\"u}ckbeil, Patrick and Weyrich, Tim},
  title = {Quantized {FCA}: Efficient Zero-Shot Texture Anomaly Detection},
  booktitle = {30th Intl. Conference on Vision, Modeling, and Visualization (VMV)},
  numpages = 10,
  day = 30,
  month = sep,
  year = 2025,
}

Related Publications

<list-of-publications>

Acknowledgments

<acknowlegments-content>