用合成数据训练汽车质检模型，效果优于真实数据。
Fully-Synthetic Training for Visual Quality Inspection in Automotive Production
- 通过领域随机化生成合成图像，自动标注缺陷。
- 纯合成数据训练的模型在三个真实场景中表现更优。
- 适合缺乏标注数据的工业质检场景。
视觉质量检测在现代制造环境中至关重要，关乎客户安全与满意度。计算机视觉（CV）技术显著提升了缺陷检测的准确性和效率。然而，传统CV模型依赖大量真实数据训练，成本高、耗时长且易出错。为此，合成图像成为有前景的替代方案，可低成本生成并自动标注。本文提出一种基于领域随机化的合成图像生成流程。我们在三个真实检测场景中评估该方法，结果表明：仅使用合成数据训练的目标检测模型，性能优于使用真实图像训练的模型。
原文摘要 · Abstract (English)
Visual Quality Inspection plays a crucial role in modern manufacturing environments as it ensures customer safety and satisfaction. The introduction of Computer Vision (CV) has revolutionized visual quality inspection by improving the accuracy and efficiency of defect detection. However, traditional CV models heavily rely on extensive datasets for training, which can be costly, time-consuming, and error-prone. To overcome these challenges, synthetic images have emerged as a promising alternative. They offer a cost-effective solution with automatically generated labels. In this paper, we propose a pipeline for generating synthetic images using domain randomization. We evaluate our approach in three real inspection scenarios and demonstrate that an object detection model trained solely on synthetic data can outperform models trained on real images.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。