The problems of dense stereo reconstruction and object class segmentation can both be formulated as Conditional Random Field based labelling problems, in which every pixel in the ...
Lubor Ladicky, Paul Sturgess, Christopher Russell,...
This paper introduces two novel beamforming algorithms, namely the Region Constrained and Multiple Correlated Source Model beamformers, designed to localize and to reconstruct hig...
This paper summarizes a series of recent research results made at Edinburgh University based applying domain knowledge of standard shapes and relationships to solve or improve arc...
We present a method to improve the quality of cone-beam tomographic images computed from an intra-operative C-arm scan by adding information from an anatomical atlas. Limited rang...
— Building an accurate three dimensional map is an important task for autonomous localisation and navigation. In a sequential approach to reconstruction from video streams, we sh...