We introduce a new structural constraint that can be used for matching points in image pairs taken from a wide baseline. No assumption is made about the geometry of the 3?D points...
`Invariant regions' are image patches that automatically deform with changing viewpoint as to keep on covering identical physical parts of a scene. Such regions are then desc...
We describe and demonstrate a texture region descriptor which is invariant to affine geometric and photometric transformations, and insensitive to the shape of the texture region....
This paper describes a novel approach to automatically recover corresponding feature points and epipolar geometry over two wide baseline frames. Our contributions consist of sever...
In this paper we describe a dense motion segmentation method for wide baseline image pairs. Unlike many previous methods our approach is able to deal with deforming motions and lar...
Juho Kannala, Esa Rahtu, Sami S. Brandt, Janne Hei...