My interests are in generative models, approximate inference and deep learning. Currently my research is focused on 3D shape modelling for computer vision applications.
Overcoming Occlusion with Inverse Graphics.
Pol Moreno, Chris Williams, Charlie Nash and Pushmeet Kohli, European Conference of Computer Vision (ECCV), Geometry meets Deep Learning Workshop, 2016.
We introduce a generative model of part-segmented 3D objects: the shape variational auto-encoder (ShapeVAE).
The ShapeVAE describes a joint distribution over the existence of object parts, the locations of a dense set of surface points, and over surface normals associated with these points. Our model makes use of a deep encoder-decoder architecture that leverages the part-decomposability of 3D objects to embed high-dimensional shape representations and sample novel instances.
The ShapeVAE is capable of synthesizing novel shapes, and by performing conditional inference enables imputation of missing parts or surface normals. In addition, by generating both points and surface normals, our model allows for the use of powerful surface-reconstruction methods for mesh synthesis.
For more information please see the paper
A model of object shape can be very useful for computer vision applications, whether as a means of generating richly-annotated training data for a recognition model, or as a component in an inverse-graphics system.
In this project we develop a system that can generate novel instances of an object class, using a collection of examples from that object class as training data. Our system establishes correspondences between landmark points on different objects, learns a generative model of the point locations, samples landmark points using the model and then meshes the shape samples.
Electroencephalograms (EEGs) can record electrical activity in the brain. In conjunction with a brain-computer interface (BCI) they can be used to augment human sensory functions or control robotic devices.
In this project we use EEG inputs to classify which of three tasks a subject is performing. We apply feature selection, then use Random Forests with temporal smoothing to classify each time point.
MATLAB implementation of a non-rigid variant of the iterative closest point algorithm. It can be used to register 3D surfaces or point-clouds. The method is described in the following paper:
'Optimal Step Nonrigid ICP Algorithms for Surface Registration', Amberg, Romandhani and Vetter, CVPR, 2007.
Python implementation of Gaussian Mixture Model (GMM) variants.
Before starting my PhD, I did a Masters by Research in Data Science (as part of the CDT in Data Science) at Edinburgh. My MSc thesis was on 3D shape modelling and was supervised by Chris Williams.
Prior to that, I did my undergraduate degree also at Edinburgh where I studied Mathematics.