We present a scalable and incremental approach for creating interactive image-based walkthroughs from a dynamically growing collection of photographs of a scene. Prior approaches, such as [16], perform a global scene reconstruction as they require the knowledge of all the camera poses. These are recovered via batch processing involving pairwise image matching and structure from motion (Sfm), on...

In [1] Murray et al. describe a motion processing system, ISOR, which is able to recover the 3D motion and structure of polyhedral objects from an image sequence and goes on, where possible, to recognize the object as one from a database of object models. The system performs a 'bottomup' pass through a vision processing hierarchy in the four stages: (i) Low level Compute visual motion at intens...

Intelligent agents are often called upon to form plans that direct their own or other agents' activities. For these systems, the ability to describe plans to people in natural ways is an essential aspect of their interface. In this paper, we present the Cooperative Plan Identi cation (CPI) architecture, a computational model that generates concise, e ective textual descriptions of plan data str...

The recovery of 3D shape and camera motion for non-rigid scenes from single-camera video footage is a very important problem in computer vision. The low-rank shape model consists in regarding the deformations as linear combinations of basis shapes. Most algorithms for reconstructing the parameters of this model along with camera motion are based on three main steps. Given point tracks and the r...

We investigate the mis-match in the classical interpretation of certain distribution-fitting problems as maximum-likelihood (ML) estimation problems in the particular case of the I-divergence. The general relation between Bregman divergences and exponential families shown by Banerjee et al. [8] enables to consider distribution-fitting problems based on Bregman divergences as ML problems based o...

The problem of structure from motion (SFM) is to extract the three-dimensional model of a moving scene from a sequence of images. Most of the algorithms which work by fusing the two-frame depth estimates (observations) assume an underlying statistical model for the observations and do not evaluate the quality of the individual observations. However, in real scenarios, it is often difficult to j...

The purpose of this chapter is to exemplify construction of selected Coupling-from-the-Past algorithms, using simple examples and discussing code which can be run in the statistical scripting language R. The simple examples are: symmetric random walk with two reflecting boundaries, a very basic continuous state-space Markov chain, the Ising model with external field, and random walk with negati...

The seasonal variation in lower trophic level ecosystem of Hakata Bay, Japan is investigated using observed data from April 1993 to March 1994 and a numerical ecosystem model. Primary production was largest in September 1993 due to high DIP concentration but secondary production was largest in August 1993 due to high water temperature. Yearly averaged primary production in Hakata Bay is larger ...

Intelligent systems are often called upon to form plans that direct their own or other agents' activities. For these systems, the ability to describe plans to people in natural ways is an essential aspect of their interface. In this paper, I present the Cooperative Plan Identi cation (CPI) architecture, a computational model that generates concise, e ective textual descriptions of plans. In thi...

This is the era of digital landscapes; the widespread availability of powerful sensing technologies has revolutionized the way it is possible to interrogate landscapes in order to understand the processes sculpting them. Vastly greater areas have now been acquired at ‘high resolution’: currently 10s of m globally to millimetric precision and accuracy locally. This permits geomorphic features to...