CAD2Render: A Modular Toolkit for GPU-accelerated Photorealistic Synthetic Data Generation for the Manufacturing Industry

TL;DR

CAD2Render is a GPU-accelerated, modular synthetic data generator that leverages CAD models to produce customizable, photorealistic images for training machine learning models in manufacturing, improving performance in quality control tasks.

Contribution

This paper introduces CAD2Render, a novel, highly customizable GPU-based toolkit for generating synthetic data from CAD models tailored for manufacturing applications.

Findings

Achieves state-of-the-art performance in object detection and pose estimation tasks.

Enables training of models capable of guiding robotic operations.

Demonstrates high accuracy with synthetic data in industrial scenarios.

Abstract

The use of computer vision for product and assembly quality control is becoming ubiquitous in the manufacturing industry. Lately, it is apparent that machine learning based solutions are outperforming classical computer vision algorithms in terms of performance and robustness. However, a main drawback is that they require sufficiently large and labeled training datasets, which are often not available or too tedious and too time consuming to acquire. This is especially true for low-volume and high-variance manufacturing. Fortunately, in this industry, CAD models of the manufactured or assembled products are available. This paper introduces CAD2Render, a GPU-accelerated synthetic data generator based on the Unity High Definition Render Pipeline (HDRP). CAD2Render is designed to add variations in a modular fashion, making it possible for high customizable data generation, tailored to the needs of the industrial use case at hand. Although CAD2Render is specifically designed for manufacturing use cases, it can be used for other domains as well. We validate CAD2Render by demonstrating state of the art performance in two industrial relevant setups. We demonstrate that the data generated by our approach can be used to train object detection and pose estimation models with a high enough accuracy to direct a robot. The code for CAD2Render is available at https://github.com/EDM-Research/CAD2Render.