Talk to sales Try for Free
Laurent Gudemann

Laurent gudemann

bookmark on deepenrich
location of Laurent GudemannMunich, Bavaria, Germany
Phone number of Laurent GudemannView Mobile No.
Followers of Laurent Gudemann366 followers

  • Timeline

  • About me

    Taking smartphone cameras to the next level as Machine Learning Engineer at GLASS Imaging

  • Education

    • Stuttgart media university

      2021 - 2023
      Master of science - ms computer science and media note 1,1 / 3.9 gpa

    • Hochschule der medien stuttgart

      2017 - 2021
      Bachelor of engineering - be audiovisual media note 1,1 / 3.9 gpa

    • California state university-los angeles

      2020 - 2020
      Year abroad television film and media studies 4.0 gpa / note 1,0

      Activities and Societies: Recipient of DAAD HAW.International and DAAD PROMOS Scholarships

  • Experience

    • Arri

      Aug 2019 - Dec 2019
      Engineering intern - image science

      • Processed ARRIRAW bayer pattern images in Matlab• Conducted tests for ALEXA 35 prototypes, lenses, and lighting• Used Baselight system for color managing and screening footage

    • Arri

      Apr 2021 - Aug 2021
      Bachelor's thesis - image science

      Developed a display-to-camera calibration and camera color processing system for LED wall mixed reality production studios using non-linear color correction methods.My research was later published as a paper titled "Color Reproduction in LED Wall Virtual Production Stages" at the 30th Color & Imaging Conference.

    • Stuttgart media university

      Mar 2022 - Jul 2022
      Lecturer for advanced film technology

      Taught an undergraduate class on camera image processing pipelines in Matlab. Topics included color space conversion, debayering, camera characterization, and display rendering.

    • Arri

      Nov 2022 - Aug 2023
      Master's thesis - image science

      "Deep Learning for Joint Video Denoising and Debayering" Supervised by Prof. Dr. Johannes Maucher• Designed novel neural network architectures, datasets, and training methods for deep-learning-based joint video denoising and debayering.• Optimized the model architectures for efficient inference on modern NVIDIA GPUs using INT8 quantization aware training and TensorRT.• Demonstrated competitive image quality with offline post-production video denoising software (including the market leader Neat Video) within real-time performance constraints. The proposed model achieves 32 ms runtime (31 FPS) at 14 megapixel resolution on an NVIDIA RTX A6000 GPU. Show less

    • Pro-beam group

      May 2024 - Jun 2024
      Image processing engineer

    • Glass imaging

      Jul 2024 - now
      Machine learning engineer

  • Licenses & Certifications