A Scalable Pipeline Combining Procedural 3D Graphics and Guided Diffusion for Photorealistic Synthetic Training Data Generation in White Button Mushroom Segmentation
Computers and Electronics in Agriculture · 2026-11 · 254 · 112269
DOI: 10.1016/j.compag.2026.112269 ↗Kurz gefasst
Fachartikel in der Zeitschrift Computers and Electronics in Agriculture, 2026-11. Verfasst von Artúr I. Károly und 1 weiteren Autor:innen. Die Arbeit nennt 66 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Research Development and Innovation Office, Nemzeti Kutatási, Fejlesztési és Innovaciós Alap, Obuda University.
Abstract (Originalsprache)
Industrial mushroom cultivation increasingly relies on computer vision for monitoring and automated harvesting. However, developing accurate detection and segmentation models requires large, precisely annotated datasets that are costly to produce. Synthetic data provides a scalable alternative, yet often lacks sufficient realism to generalize to real-world scenarios. This paper presents a novel workflow that integrates 3D rendering in Blender with a constrained diffusion model to automatically generate high-quality annotated, photorealistic synthetic images of Agaricus Bisporus mushrooms. This approach preserves full control over 3D scene configuration and annotations while achieving photorealism without the need for specialized computer graphics expertise. We release two synthetic datasets (each containing 6000 images depicting over 250k mushroom instances) and evaluate Mask R-CNN models trained on them in a zero-shot setting. When tested on two independent real-world datasets (including a newly collected benchmark), our method achieves state-of-the-art segmentation performance (F1 = 0.859 on M18K), despite using only synthetic training data. Although the approach is demonstrated on Agaricus Bisporus mushrooms, the proposed pipeline can be readily adapted to other mushroom species or to other agricultural domains, such as fruit and leaf detection.
Förderung
- National Research Development and Innovation Office
- Nemzeti Kutatási, Fejlesztési és Innovaciós Alap
- Obuda University
Zitieren
APA
Károly, A. I., & Galambos, P. (2026). A Scalable Pipeline Combining Procedural 3D Graphics and Guided Diffusion for Photorealistic Synthetic Training Data Generation in White Button Mushroom Segmentation. Computers and Electronics in Agriculture, 254, 112269. https://doi.org/10.1016/j.compag.2026.112269
Vancouver
Károly AI, Galambos P. A Scalable Pipeline Combining Procedural 3D Graphics and Guided Diffusion for Photorealistic Synthetic Training Data Generation in White Button Mushroom Segmentation. Computers and Electronics in Agriculture. 2026;254:112269. doi:10.1016/j.compag.2026.112269
BibTeX
@article{Kroly2026,
author = {Károly, Artúr I. and Galambos, Péter},
title = {A Scalable Pipeline Combining Procedural 3D Graphics and Guided Diffusion for Photorealistic Synthetic Training Data Generation in White Button Mushroom Segmentation},
journal = {Computers and Electronics in Agriculture},
year = {2026},
volume = {254},
pages = {112269},
doi = {10.1016/j.compag.2026.112269}
}
EUVIMED