Intern: Software Engineering, Multi-View 3D Reconstruction
Apply nowReady to apply?
You will be taken to the company's application page to apply directly.
Multi-View Stereo (MVS)Deep LearningC++Point Cloud ProcessingCOLMAPPythonStructure from Motion (SfM)PCLOpen3DPhotogrammetry
Intrinsic is an AI robotics group at Google aiming to reimagine the potential of industrial robotics. Our team believes that advances in AI, perception and simulation will redefine what’s possible for industrial robotics in the near future – with software and data at the core.
Our mission is to make industrial robotics intelligent, accessible, and usable for millions more businesses, entrepreneurs, and developers. We are a dynamic team of engineers, roboticists, designers, and technologists who are passionate about unlocking the creative and economic potential of industrial robotics.
Role
Are you passionate about democratizing robotics and making cutting-edge technology accessible for all? We are seeking highly motivated and talented interns to join our dynamic team and contribute to the advancement of robotics in an exciting internship opportunity.
How your work moves the mission forward
If you have a disability or special need that requires accommodation, please contact us at: [email protected].
Our mission is to make industrial robotics intelligent, accessible, and usable for millions more businesses, entrepreneurs, and developers. We are a dynamic team of engineers, roboticists, designers, and technologists who are passionate about unlocking the creative and economic potential of industrial robotics.
Role
Are you passionate about democratizing robotics and making cutting-edge technology accessible for all? We are seeking highly motivated and talented interns to join our dynamic team and contribute to the advancement of robotics in an exciting internship opportunity.
How your work moves the mission forward
- Develop and implement a dense multi-view reconstruction pipeline using posed images to generate accurate 3D ground truth for single shot reconstruction algorithms.
- Apply Deep learning based Structure from Motion (SfM) techniques to create a robust benchmark for evaluating point-cloud models.
- Analyze reconstruction quality and, if necessary, integrate and calibrate additional 3D sensors into the data collection setup to ensure high fidelity and completeness.
- Collaborate with the perception team to validate ground-truth pipelines and support the direct evaluation of advanced perception algorithms.
- Contribute to the improvement of internal data tools by establishing reliable standards for point-cloud accuracy.
- Bachelor’s student in Computer Science, Robotics, Computer Vision, or a related field (Master's students preferred).
- Strong proficiency in C++ and/or Python for software development and algorithm implementation.
- Experience with 3D computer vision concepts, specifically Structure from Motion (SfM), Multi-View Stereo (MVS), or photogrammetry.
- Familiarity with point cloud processing, 3D geometry, and linear algebra.
- Experience with 3D vision libraries and tools (e.g., COLMAP, Open3D, PCL, or similar).
- Enthusiasm for solving challenging problems in benchmarking, data evaluation, and perception algorithms.
If you have a disability or special need that requires accommodation, please contact us at: [email protected].