Projects

Current and past research projects. Filter by status or research theme.

3D Reconstruction Computer Vision Intelligent Transport Systems Machine Learning Monocular Depth Estimation Photometric Stereo Reinforcement Learning

Completed

Vision, Language and Visual Retrieval

Multimodal methods connecting images and language: large-scale visual retrieval, semantic art understanding, and image caption generation.

Computer Vision Machine Learning

Completed

Self-Supervised Monocular Depth Estimation

Learning to predict depth from single images without ground-truth supervision, with a focus on dynamic scenes and challenging conditions.

Computer Vision Machine Learning Monocular Depth Estimation

Completed

Photometric Stereo and Shape from Shading

Recovering surface normals, shape, and reflectance from images captured under varying illumination — including coloured-light, multi-spectral, and shadow-robust methods.

3D Reconstruction Photometric Stereo

Completed

3D Reconstruction and Multi-View Stereo

Recovering accurate 3D shape from collections of images, using multi-view stereo, volumetric graph-cuts, and probabilistic depth-map fusion.

3D Reconstruction Computer Vision