| CARVIEW |
Biography
I am currently a Senior Lecturer in IDCOM at the University of Edinburgh, working on Computer Vision and Machine Learning problems. Recent research directions include multi-modal, multi-task learning and medical imaging applications.
Previously I was a Senior Research Scientist with Huawei Technologies’ Noah’s Ark lab and have also held postdoctoral positions with the Biomedical Image Analysis Group, Imperial College London, working with Prof. Ben Glocker, Dr. Bernhard Kainz and Prof. Daniel Rueckert and, prior to that, with Disney Research Zurich working on real-time facial performance capture. I earned my PhD at the University of Edinburgh in the Institute of Perception, Action and Behaviour under the supervision of Prof. Bob Fisher for my work on density estimation and multi-view 3D point set registration.
I am a member of the Edinburgh ELLIS Unit, Vision Group and the VIOS collaboratory, where my interests span topics in Computer Vision, Machine Learning and Medical Image Analysis. You can occasionally find me up a mountain; running or cycling.
Interests
- Computer Vision
- Machine Learning
- Medical Image Analysis
- Artificial Intelligence
Education
-
PhD in Computer Vision, 2015
University of Edinburgh
-
BSc (Hons) in Artificial Intelligence and Computer Science, 2008
University of Edinburgh
Selected publications
Learning to Name Classes for Vision and Language Models
Spread Flows for Manifold Modelling
Content-Diverse Comparisons improve IQA
Residual Contrastive Learning for Image Reconstruction: Learning Transferable Representations from Noisy Images
CroMo: Cross-Modal Learning for Monocular Depth Estimation
On the Out-of-distribution Generalization of Probabilistic Image Modelling
A Multi-Hypothesis Approach to Color Constancy
Formulating Camera-Adaptive Color Constancy as a Few-shot Meta-Learning Problem
SteReFo: Efficient Image Refocusing with Stereo Vision
Attention U-Net: Learning Where to Look for the Pancreas
Context-Sensitive Super-Resolution for Fast Fetal Magnetic Resonance Imaging
Ensembles of Multiple Models and Architectures for Robust Brain Tumour Segmentation
Predicting Slice-to-Volume Transformation in Presence of Arbitrary Subject Motion
PVR: Patch-to-Volume Reconstruction for Large Area Motion Correction of Fetal MRI
Noise Reduction on G‐Buffers for Monte Carlo Filtering
Synthetic Prior Design for Real-time Face Tracking
Real-Time Multi-View Facial Capture with Synthetic Training
Adaptive Polynomial Rendering
Fusing 100’s of 3D Point Clouds of Objects
Laminar and Dorsoventral Molecular Organization of the Medial Entorhinal Cortex Revealed by Large-scale Anatomical Analysis of Gene Expression
Interactive light source position estimation for augmented reality with an RGB-D camera
Applying semi-synchronised task farming to large-scale computer vision problems
Simultaneous registration of multi-view range images with adaptive kernel density estimation
Point Light Source Estimation based on Scenes Recorded by a RGB-D camera
Using 3D information for classification of non-melanoma skin cancer
Teaching
- Lecturer: Machine Learning in Signal Processing (MSc) - www - (2023-24).
Previously, I have taught:
- Guest lecturer: Computer Vision INM460/IN3060 (UG4/MSc), City, University of London (2021).
- Teaching Assistant: Mathematical Methods CO-145 (UG1), Imperial College London (2017).
- Teaching Assistant: Machine Learning and Neural Computation (MSc), Imperial College London (2016).
- Guest lecturer: Advanced Computer Vision (UG4/MSc), Edinburgh (2014).
- Teaching Assistant: Advanced Computer Vision (UG4/MSc), Edinburgh (2012–2014).
- Teaching Assistant: Introduction to Vision and Robotics (UG3), Edinburgh (2011-2012).
Contact
- s.mcdonagh(at)ed(dot)ac(dot)uk
- King's Buildings, Thomas Bayes Rd, Edinburgh UK, EH9 3FG