Leonard Bruns
Computer Vision Researcher at Niantic Spatial, Inc.
London, England, United Kingdom
Summary
🤩
Rockstar🎓
Top SchoolLeonard Bruns is a computer vision researcher with nine years of experience bridging academic rigor and applied research, currently working on spatial computing at Niantic Spatial in London. He completed a PhD at KTH focused on shape and pose estimation, SLAM with neural scene representations, and visual relocalization, and has a track record of published work and patents from internships at industry leaders like Ericsson and Bosch. Leonard mixes strong systems and robotics roots (top-ranked degrees from RWTH Aachen and KTH) with hands-on ML engineering—contributing ControlNet/Stable Diffusion examples to the popular rerun visualization repo to make multimodal vision workflows more interpretable. He excels at turning theoretical ideas into reproducible code and demos, having shipped prototypes and contributed to ICCV-accepted work and patent filings. Colleagues would describe him as methodical, curious, and effective at translating between research proofs and production-ready experiments.
9 years of coding experience
1 year of employment as a software developer
Master of Science - MS, Systems, Control and Robotics, 3.94, Master of Science - MS, Systems, Control and Robotics, 3.94 at KTH Royal Institute of TechnologyMaster of Science - MS, Electrical Engineering, Information Technology and Computer Engineering, 1.0 (excellent) / 4.0 / top 4%, Master of Science - MS, Electrical Engineering, Information Technology and Computer Engineering, 1.0 (excellent) / 4.0 / top 4% at RWTH Aachen University
German, English, Swedish
Github Skills (9)
computer-vision10
pytorch10
visualization10
stable-diffusion10
visualizations10
python10
diffusers10
machine-learning9
rust9
Programming languages (8)
Github contributions (5)
rerun-io/rerun
Feb 2023 - Jul 2024
Visualize streams of multimodal data. Free, fast, easy to use, and simple to integrate. Built in Rust.
Role in this project:
ML Engineer
ML EngineerContributions:24 reviews, 27 PRs, 118 pushes in 1 year 5 months
Contributions summary:Leonard contributed to the project by adding an example showcasing ControlNet, a neural network architecture for image generation conditioned on an input image. This involved the implementation of a Python script utilizing the diffusers library, specifically integrating with Stable Diffusion XL. The code logs intermediate states and the final output, demonstrating the visualization capabilities of the project. The user also improved the examples with Markdown descriptions.
computer-visioncppmultimodalpythonrobotics
RAS18G3/everything_robot
Sep 2018 - Mar 2023
Metapackage including all required packages and code to run the robot
Contributions:28 PRs, 139 pushes, 33 branches in 4 years 6 months
metapackagerobot
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.