A Scalable Pipeline Combining Procedural 3D Graphics and Guided Diffusion for Photorealistic Synthetic Training Data Generation in White Button Mushroom Segmentation

📅 2025-12-09
📈 Citations: 0
Influential: 0
📄 PDF
🤖 AI Summary
To address the scarcity of high-quality annotated data and the prohibitive cost of manual annotation in industrial white mushroom cultivation, this paper proposes a scalable synthetic data generation framework that integrates procedural 3D modeling (Blender) with constraint-guided diffusion models. The framework enables fully automated generation of photorealistic mushroom images with pixel-accurate, instance-level semantic annotations—without requiring expertise in computer graphics. It achieves a unique balance among full controllability, annotation fidelity, and photographic realism, while supporting zero-shot domain transfer. Leveraging this pipeline, we construct two synthetic datasets, each containing 6,000 images (totaling over 250,000 mushroom instances). Training Mask R-CNN on these datasets yields state-of-the-art zero-shot segmentation performance on the real-world M18K benchmark (F1 = 0.859), significantly outperforming existing synthetic-data approaches.

Technology Category

Application Category

📝 Abstract
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 6,000 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.
Problem

Research questions and friction points this paper is trying to address.

Generates photorealistic synthetic images for mushroom segmentation training
Addresses lack of realistic synthetic data for computer vision in agriculture
Provides scalable alternative to costly manual dataset annotation
Innovation

Methods, ideas, or system contributions that make the work stand out.

Combines procedural 3D graphics with guided diffusion
Generates photorealistic synthetic images for training
Achieves state-of-the-art segmentation without real data
🔎 Similar Papers
No similar papers found.
💼 Related Jobs
No related jobs found.
A
Artúr I. Károly
Antal Bejczy Center for Intelligent Robotics, Research and Innovation Center of Obuda University, Budapest, Hungary
P
Péter Galambos
Antal Bejczy Center for Intelligent Robotics, Research and Innovation Center of Obuda University, Budapest, Hungary