Bounding Box-Guided Diffusion for Synthesizing Industrial Images and Segmentation Map

TL;DR

This paper introduces a diffusion-based method conditioned on bounding boxes to generate high-fidelity industrial images and segmentation maps, improving defect localization and realism for synthetic dataset creation.

Contribution

It presents a novel diffusion pipeline that enhances defect segmentation accuracy by conditioning on bounding boxes, advancing synthetic industrial data generation.

Findings

Improved defect localization and realism in synthetic images.

Enhanced segmentation model performance trained on synthetic data.

Quantitative metrics demonstrate the method's effectiveness.

Abstract

Synthetic dataset generation in Computer Vision, particularly for industrial applications, is still underexplored. Industrial defect segmentation, for instance, requires highly accurate labels, yet acquiring such data is costly and time-consuming. To address this challenge, we propose a novel diffusion-based pipeline for generating high-fidelity industrial datasets with minimal supervision. Our approach conditions the diffusion model on enriched bounding box representations to produce precise segmentation masks, ensuring realistic and accurately localized defect synthesis. Compared to existing layout-conditioned generative methods, our approach improves defect consistency and spatial accuracy. We introduce two quantitative metrics to evaluate the effectiveness of our method and assess its impact on a downstream segmentation task trained on real and synthetic data. Our results demonstrate that diffusion-based synthesis can bridge the gap between artificial and real-world industrial data, fostering more reliable and cost-efficient segmentation models. The code is publicly available at https://github.com/covisionlab/diffusion_labeling.