The research presented in this Ph.D. thesis is targeted towards obtaining high quality novel views of a dynamic scene using video from multiple wide-baseline views, with free-viewpoint video as the main application goal. The research has led to several novel contributions to the 3D reconstruction computer vision literature.

The first novel contribution of this work is the exact view-dependent visual hull, a method to efficiently reconstruct a three dimensional representation of the scene with respect to a given viewpoint.

A method for for producing high quality novel views through efficient local surface refinement is introduced. This reduces artefacts such as ghosting from incorrect correspondence between views when using the visual hull. A representation for rendering the refined surfaces in real-time with a user-controllable viewpoint is introduced.

An alternative method for producing high quality novel views from wide-baseline cameras using a global optimisation to refine the entire surface is presented. The goal of this is to produce a continuous surface which removes depth artefacts and represents the overall shape of the scene.

The final and most significant novel contribution of this thesis is the safe hull, the first visual hull based reconstruction method which guarantees production of a surface without phantom volumes (an artefact of visual hull reconstruction due to complicated scenes). The safe hull identifies volumes inside the visual hull which only contain foreground i.e. the object to be reconstructed. This approach uses a novel geometric constraint, utilising information gained from the exact view dependent visual hull, unlike other solutions which are either heuristic or require additional cameras.

Submitted December 2007, defended in a viva in February 2008 at the University of Surrey, U.K. (Supervisor: Adrian Hilton; External examiner: Ian Reid (University of Oxford); Internal examiner: John Illingworth; Chair: Theo Vlachos).