Charles Nicklas Christensen is a researcher specialising in computer vision, with experience in deep learning, super-resolution, image segmentation, and image classification. While working towards his PhD at the University of Cambridge, he explored computer vision techniques in the context of optical microscopy using deep learning. Some of the methods he has contributed with include ML-SIM , ERnet and VSR-SIM .
ML-SIM is a method that utilises neural networks to reconstruct structured illumination microscopy images, relying on physically modeled synthetic training data [Biomed. Opt. Express (2021) , Nature Comms. (2022) ]. ERnet is an image segmentation model for endoplasmic reticulum images that employs an architecture inspired by the vision transformer [Science Advances (2020) , Nature Methods (2023) ].
Within the industrial domain, he has contributed to the development and implementation of scalable deep learning solutions. During his time at Tesco Technology, he focused on metric learning to enable large-scale product recognition in retail environments. While at ONI, he has developed and deployed deep learning methods for spectral demixing, image segmentation, and super-resolution reconstruction in the setting of big data.
His other interests include physics, mathematical modelling, artificial intelligence and deep learning across various applications.
Download Charles Christensen’s resumé.
PhD in Computational Imaging, 2022
University of Cambridge
MRes in Image Processing and Sensing, 2018
University of Cambridge
MScEng in Mathematical Modelling and Computation, 2017
Technical University of Denmark
BScEng in Physics and Nanotechnology, 2015
Technical University of Denmark
Part-time involvement in non-profit organisation. Started as a research project doing my MRes and spun out in 2019 with five other PhD students.
Alongside my MSc studies, I worked part-time on a number of consultant jobs including: