Introducing MVTec ITODD — A Dataset for 3D Object Recognition in Industry

Abstract

We introduce the MVTec Industrial 3D Object Detection Dataset (MVTec ITODD), a public dataset for 3D object detection and pose estimation with a strong focus on objects, settings, and requirements that are realistic for industrial setups. Contrary to other 3D object detection datasets that often represent scenarios from everyday life or mobile robotic environments, our setup models industrial bin picking and object inspection tasks that often face different challenges. Additionally, the evaluation citeria are focused on practical aspects, such as runtimes, memory consumption, useful correctness measurements, and accuracy. The dataset contains 28 objects with different characteristics, arranged in over 800 scenes and labeled with around 3500 rigid 3D transformations of the object instances as ground truth. Two industrial 3D sensors and three high-resolution grayscale cameras observe the scene from different angles, allowing to evaluate methods that operate on a variety of different modalities. We initially evaluate 5 different methods on the dataset. Even though some show good results, there is plenty of room for improvement. The dataset and the results are publicly available1, and we invite others to submit results for evaluation and for optional inclusion in the result lists on the dataset's website.