— In this paper, a new statistical model is proposed for modeling the nature images in the transform domain. We demonstrate that the von Mises distribution (VM) fits accurately ...
In this paper, we presentan approach to clustering images for efficient retrieval using relative entropy. We start with the assumption that visual features are represented by prob...
Learning a generative model of natural images is a useful way of extracting features that capture interesting regularities. Previous work on learning such models has focused on me...
We describe how to model the appearance of a 3-D object using multiple views, learn such a model from training images, and use the model for object recognition. The model uses pro...
This paper presents a distributed and occlusion-robust coding scheme for multi-view omnidirectional images, which relies on the geometry of the 3D scene. The Wyner-Ziv coder uses ...