An Empirical Study of Non-Rigid Surface Feature Matching of Human from 3D Video

This paper presents an empirical study of affine invariant feature detectors to perform matching on video sequences of people with non-rigid surface deformation. Recent advances in feature detection and wide baseline matching have focused on static scenes. Video frames of human movement capture highly non-rigid deformation such as loose hair, cloth creases, skin stretching and free flowing clothing. This study evaluates the performance of six widely used feature detectors for sparse temporal correspondence on single view and multiple view video sequences. Quantitative evaluation is performed of both the number of features detected and their temporal matching against and without ground truth correspondence. Recall-accuracy analysis of feature matching is reported for temporal correspondence on single view and multiple view sequences of people with variation in clothing and movement. This analysis identifies that existing feature detection and matching algorithms are unreliable for fast movement with common clothing.

Fitting 3D morphable models using implicit representations

We consider the problem of approximating the 3D scan of a real object through an affine combination of examples. Common approaches depend either on the explicit estimation of point-to-point correspondences or on 2-dimensional projections of the target mesh; both present drawbacks. We follow an approach similar to [IF03] by representing the target via an implicit function, whose values at the vertices of the approximation are used to define a robust cost function. The problem is approached in two steps, by approximating first a coarse implicit representation of the whole target, and then finer, local ones; the local approximations are then merged together with a Poisson-based method. We report the results of applying our method on a subset of 3D scans from the Face Recognition Grand Challenge v.1.0.

The Benefits of Multilingualism for Statutory and Constitutional Interpretation in South Africa

Taking the South African experience as an example, this article considers the interpretive benefits to be reaped from having access to bi- and multilingual versions of a statutory text. The discussion takes place against the backdrop of a history of statutory bi- and multilingualism in the said jurisdiction as well as, at present, constitutional guarantees of language rights and the “parity of esteem” of eleven official languages. It is argued that, if invoked with due discretion and in a non-rigid way, statutory multilingualism can be a boon to statutory and constitutional interpretation. The South African courts – whose traditional approach to statutory inter-pretation has tended to be literalist, formalistic and formulaic – are, generally speaking, to be commended for their supple use of bilingualism as an aid to interpretation over the years. The advent of constitutional multilingualism and the (potential) availability of statutory texts (and the Constitution) in more than two languages, have moreover created conditions conducive to the further development and refinement of reliance on multilingualism in statutory and constitutional interpretation – certain challenges notwithstanding.