The non-existence of general-case view-invariants

By J. Burns, R. Weiss, E. Riseman. 1992

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Towards a Definition of Disentangled Representations (2018, background): “While classic work showed that there are no general-purpose features for 3D point clouds that are invariant to changes in viewpoint [14], later work on more realistic models of images showed that features simultaneously invariant to changes in illumination and viewpoint do in fact exist [71].”
In search of illumination invariants (2001, background): “, [7, 51]); they are sometimes relaxed versions of invariant properties.”
Object Recognition in the Geometric Era: A Retrospective (2006, background): “…by geometric invariance: – it was proved independently by several researchers that no viewpoint invariants exist for general 3-d shapes [18, 14, 51]; – the grouping problem re-emerges; it is necessary to associate a rather large number of features (e.g. ﬁve lines) across views in order to…”
On the set of images modulo viewpoint and contrast changes (2009, background): “For the case of viewpoint, although earlier literature [3] suggested that general-case view-invariants do not exist, it has been shown that it is always possible to construct non-trivial viewpoint invariant image statistics for Lambertian objects of any shape [13].”