LOG OUT
| Feature Presentation, HALCON

Deep 3D Matching in MVTec HALCON

Deep 3D Matching is a new deep-learning-based technology for fast and robust 3D object detection and pose estimation using 2D images. It requires minimal parametrization and delivers high performance, making it ideal for applications such as bin picking and robotic handling – even in challenging conditions.

This video shows a detailed presentation of the feature Deep 3D Matching in MVTec HALCON during MVTec Innovation Day 2025.

Content

00:00 Introduction: Why do we need the position of an object in space?
05:02 What is Deep 3D Matching?
15:46 Which method for localization of objects in MVTec HALCON do I need when?
22:08 Internal workflow of Deep 3D Matching
24:46 Live-demonstration
33:52 Final pipeline: training, calibration, inference
40:37 Summary

Please note: Once you watch the video, data will be transmitted to Youtube/Google. For more information, see Google Privacy.

Back

Related Links