Charles Nicklas Christensen

PhD
Computer Vision & AI

University of Cambridge

Biography

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.

Interests

Computer Vision
Image Analysis
Deep Learning
Super-resolution
Computational Imaging

Education

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

Experience

AI/ML Scientist

GSK

Oct 2023 – Present London, UK

Machine learning research scientist in the AI/ML team at GSK.

Deep learning
Computer vision
Pytorch

Machine Learning Research Scientist

Oxford Nanoimaging, ONI

Apr 2022 – Oct 2023 Oxford, UK

Developed and deployed deep learning methods for spectral demixing, image segmentation, and super-resolution towards new product offerings. This involved R&D and MLOps. In addition to this, I have also contributed to a web-based acquisition and analysis software which involves several technologies spanning front-end, back-end and deployment.

Python
C++
Image processing
Deep learning
Pytorch
CNNs

Co-founder & CTO

Wizion AI

Oct 2019 – Sep 2022 Cambridge, UK

Together with a colleague from my research group, I co-founded Wizion AI, a company offering image processing products utilising deep learning methods inspired by research in our lab. In 2020, we were selected for the Cambridge Accelerate accelerator programme at the Judge Business School. After three years of efforts towards the development of two products, we decided to shift our focus to other opportunities.

Computer vision
MLOps
Image processing

Computer Vision Research Scientist

Tesco Technology

Jul 2021 – Oct 2021 London, UK

Within the Tesco Data Science department, I worked with the computer vision team on large-scale image classification for product recognition at the till to prevent theft.

Metric learning
Transformers
Pytorch
Pandas
TensorRT

Co-founder & Head of Data

Open-seneca

Jun 2018 – Present Cambridge, UK

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.

Open-source hardware design of air quality monitor.
Deployment of sensor networks in several countries across South America, Africa, Europe and Asia.
More information https://open-seneca.org

Big data
Data visualisation
Python
Scikit-learn
MongoDB

Research Associate

Physical Computation Lab

Jul 2018 – Jan 2019 Department of Engineering, Cambridge University, UK

I worked with Professor Phillip Stanley-Marbell, head of the Physical Computation Lab. In the research project, I modelled lightness illusions in the human visual system by attempting to reproduce them with artificial neural networks.

Research Assistant

Danish Fundamental Metrology

May 2017 – Aug 2017 Lyngby, Denmark

Researched and developed a machine learning system for a novel laser based fire detector. This involved optical engineering and signal processing using machine learning techniques.

Signal processing
Time-series classification
Support vector machines

Data Consultant

VisionTrace

Sep 2017 – Dec 2016 Lyngby, Denmark

Alongside my MSc studies, I worked part-time on a number of consultant jobs including:

Developed a system for image analysis of a continuous video feed at a production facility overseen by food industry technology provider GEA.
Performed data mining on a big dataset for Danish television broadcaster TV2 with results used in a program about fitness level.

Video tracking
Data mining

Research Assistant

Department of Photonics Engineering

Sep 2017 – Jul 2017 Technical University of Denmark

Further researched the topic of my BSc thesis and wrote it up as a publication.

Markov processes
Quantum mechanics
Algebraic computation
Mathematica

Publications

Meng Lu, Charles Nicklas Christensen, Jana M. Weber, Tasuku Konno, Nino F. Läubli, Katharina M. Scherer, Edward Avezov, Pietro Lio, Alexei A. Lapkin, Gabriele S. Kaminski Schierle, Clemens F. Kaminski (2023). ERnet: a tool for the semantic segmentation and quantitative analysis of endoplasmic reticulum topology. In Nature Methods.

PDF Cite DOI GitHub

Edward N. Ward, Lisa Hecker, Charles Nicklas Christensen, Jacob R. Lamb, Meng Lu, Luca Mascheroni, Chyi Wei Chung, Anna Wang, Christopher J. Rowlands, Gabriele S.Kaminski Schierle, Clemens F. Kaminski (2022). MAI-SIM: interferometric multicolor structured illumination microscopy for everybody. In Nature Communications.

PDF Cite DOI GitHub

Charles Nicklas Christensen, Meng Lu, Edward N. Ward, Pietro Lio, Clemens F. Kaminski (2022). Spatio-temporal Vision Transformer for Super-resolution Microscopy. On arXiv.

PDF Cite DOI GitHub

Charles Nicklas Christensen, Edward N. Ward, Meng Lu, Pietro Lio, Clemens F. Kaminski (2021). ML-SIM : Universal reconstruction of structured illumination microscopy images using transfer learning. In Biomedical Optics Express.

PDF Cite DOI GitHub

Charles Nicklas Christensen, Yevgen Zainchkovskyy, Salvador Barrera-Figueroa, Antoni Torras-Rosell, Giorgio Marinelli, Kim Sommerlund-Thorsen, Jan Kleven, Mikael Lassen (2021). Simple and robust speckle detection method for fire and heat detection in harsh environments. In Applied Optics.

PDF Cite DOI

See all publications