New wave of open source capabilities in 3D vision

Skip to content


Open for business: New wave of open source capabilities in 3D vision

Open for business: New wave of open source capabilities in 3D vision


Part 1

As robust depth cameras become more affordable, many new products will benefit from true 3D vision. This presentation will highlight the benefits of depth sensing for tasks such as autonomous navigation, collision avoidance and object detection in robots and drones. We will assemble a fully functional SLAM pipeline using free and open-source software components and off-the-shelf Intel RealSense D435i depth camera, and see how it performs for real-time environment mapping and tracking.

Sergey is the maintainer of the Intel RealSense open-source project and a manager at Intel. He has been with Intel RealSense for five years, leading the transformation of Intel RealSense into an open, multi-platform technology. Before joining Intel, Sergey developed and managed multiple advanced computer vision projects. He has a bachelor’s degree in mathematics and computer science from the Ben-Gurion University, Israel. Sergey has had a life-long fascination with technology, and enjoys contributing to open-source projects (including the Linux kernel) as well as speaking and writing about software engineering.

Learn more about depth cameras

Part 2

Open3D is a modern open-source library for 3D data processing. It implements a comprehensive set of 3D data structures and supports various 3D data processing algorithms, such as point cloud registration, color map optimization, scene reconstruction, 3D visualization and more. Open3D provides C++ and Python APIs, has cross-platform support for Ubuntu/macOS/Windows, and it can be installed with pip, conda or build from source with ease. In this presentation, we will first do a brief introduction of Open3D by walking through the installation process, basic usage and the supported 3D data structures (point cloud, triangle mesh, voxel grid, octree, etc.). Then, we will move on to various applications build on top of Open3D, including LIDAR semantic segmentation with Open3D and PointNet++, 3D scene capturing and reconstruction with Intel RealSense camera, and color map optimization of 3D geometry.

Yixing Lao is a research engineer at Intel Intelligent Systems Lab, working on Open3D and projects on 3D computer vision and graphics. Before that, he was a machine learning engineer at Intel AI group, working on deep learning compiler nGraph for neural network accelerators. Yixing did his master’s in computer science at UC San Diego and undergrad at the University of Hong Kong.

Learn more about Open3D

to receive updates about our latest blog posts and other news.

Let’s talk about how Intel RealSense computer vision products can enhance your solution.

By submitting this form, you are confirming you are an adult 18 years or older and you agree to share your personal information with Intel to use for this business request. You also agree to subscribe to stay connected to the latest Intel technologies and industry trends by email and telephone. You may unsubscribe at any time. Intel’s web sites and communications are subject to our Privacy Notice and Terms of Use.

Scroll To Top