Oliver J. Woodford

Learn More
Second-order priors on the smoothness of 3D surfaces are a better model of typical scenes than first-order priors. However, stereo reconstruction using global inference algorithms, such as graph cuts, has not been able to incorporate second-order priors because the triple cliques needed to express them yield intractable (nonsubmodular) optimization(More)
In recent years the Markov Random Field (MRF) has become the de facto probabilistic model for low-level vision applications. However, in a maximum a posteriori (MAP) framework, MRFs inherently encourage delta function marginal statistics. By contrast, many low-level vision problems have heavy tailed marginal statistics, making the MRF model unsuitable. In(More)
Image priors for novel view synthesis have traditionally been non-parametric models based on large libraries of image patch exemplars, producing highquality results but making inference very slow. Recently a parametric framework, called Fields of Experts, has been proposed for image restoration that promises to speed up inference dramatically. In this paper(More)
New-view synthesis (NVS) using texture priors (as opposed to surface-smoothness priors) can yield high quality results, but the standard formulation is in terms of large-clique Markov random fields (MRFs). Only local optimization methods such as iterated conditional modes, which are prone to fall into local minima close to the initial estimate, are(More)
We show that application of modern multiview stereo techniques to the newview synthesis (NVS) problem introduces a number of non-trivial complexities. By simultaneously solving for the colour and depth of the new-view pixels we can eliminate the visual artefacts that conventional NVS-via-stereo suffers. The global occlusion reasoning which has led to(More)
In applying the Hough transform to the problem of 3D shape recognition and registration, we develop two new and powerful improvements to this popular inference method. The first, intrinsic Hough, solves the problem of exponential memory requirements of the standard Hough transform by exploiting the sparsity of the Hough space. The second, minimum-entropy(More)
This paper presents the first performance evaluation of interest points on scalar volumetric data. Such data encodes 3D shape, a fundamental property of objects. The use of another such property, texture (i.e. 2D surface colouration), or appearance, for object detection, recognition and registration has been well studied; 3D shape less so. However, the(More)
Novel view synthesis using image-based priors has recently been shown to provide high quality renderings of complex 3D scenes. However, current methods are extremely slow, requiring of the order of hours to render a single frame. In this paper we show how a coarse-to-fine method can be used to reduce this time significantly. In contrast to traditional(More)
This paper presents a method for vote-based 3D shape recognition and registration, in particular using mean shift on 3D pose votes in the space of direct similarity transforms for the first time. We introduce a new distance between poses in this space—the SRT distance. It is left-invariant, unlike Euclidean distance, and has a unique, closed-form(More)