SIMULDITEX: Single Image Multiscale & Lightweight Diffusion for Texture Modelling


Pierrick Chatillon (Université de Caen Normandie), Julien Rabin (Université de Caen Normandie), David Tschumperlé (Université de Caen Normandie)
The 35th British Machine Vision Conference

Abstract

We propose SIMuLDiTex, a Single Image Multi-scale and Light-weight Diffusion Texture model. While traditional patch-based methods are fast, they often fail to preserve complex texture details and generalize from limited examples. Recent generative models, though effective, suffer from high computational costs and memory requirements. Our approach addresses these challenges by employing a coarse-to-fine strategy that accelerates sampling and maintains high-resolution fidelity without the need for auto-encoders. We introduce a scale conditioning mechanism, enabling the use of a single network with only one million parameters. Experiments demonstrate that SIMuLDiTex outperforms existing methods in speed, quality, and scalability, offering a practical solution for real-time, high-resolution texture generation.

Citation

@inproceedings{Chatillon_2025_BMVC,
author    = {Pierrick Chatillon and Julien Rabin and David Tschumperlé},
title     = {SIMULDITEX: Single Image Multiscale & Lightweight Diffusion for Texture Modelling},
booktitle = {36th British Machine Vision Conference 2025, {BMVC} 2025, Sheffield, UK, November 24-27, 2025},
publisher = {BMVA},
year      = {2025},
url       = {https://bmva-archive.org.uk/bmvc/2025/assets/papers/Paper_832/paper.pdf}
}


Copyright © 2025 The British Machine Vision Association and Society for Pattern Recognition
The British Machine Vision Conference is organised by The British Machine Vision Association and Society for Pattern Recognition. The Association is a Company limited by guarantee, No.2543446, and a non-profit-making body, registered in England and Wales as Charity No.1002307 (Registered Office: Dept. of Computer Science, Durham University, South Road, Durham, DH1 3LE, UK).

Imprint | Data Protection