This paper presents a new approach to integrate the gradient field to the relative depth or height map from multiple view directions in polar coordinates. Traditional integration ...
For object recognition under varying illumination conditions, we propose a method based on photometric alignment. The photometric alignment is known as a technique that models bot...
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....
—In this paper, we introduce a local image descriptor, DAISY, which is very efficient to compute densely. We also present an EM-based algorithm to compute dense depth and occlusi...
This paper addresses scene understanding in the context of a moving camera, integrating semantic reasoning ideas from monocular vision with 3D information available through struct...