based on information about where flow is likely to be accurate. A Bayesian matting technique uses the flowed trimaps to yield high-quality mattes of moving foreground elements with complex boundaries filmed by a moving camera. A novel technique for smoke matte extraction is also demonstrated. CR

Abstract — This paper combines grasp analysis and manipulation planning techniques to perform fast grasp planning in complex scenes. In much previous work on grasping, the object being grasped is assumed to be the only object in the environment. Hence the grasp quality metrics and grasping

Simulating realistic lighting and rendering complex scenes are usually considered separate problems with incompatible solutions. Accurate lighting calculations are typically performed using ray tracing algorithms, which require that the entire scene database reside in memory to perform well

Abstract. We present an image segmentation technique using the mor-phological Waterfall algorithm. Improvements in the segmentation are brought about by using improved gradients. These are based on the detection of object boundaries learnt from human segmentations intro-duced by Martin et al. (2004). We avoid the usual pitfall found when applying Watershed algorithms to these boundaries, namely that the boundary lines usually contain gaps, by making use of distance func-tions on the boundary image. Two types of distance function are used: the classic distance function and a distance function for numerical images recently introduced by Beucher (2005). Resulting segmentations are com-pared to human segmentations using the Berkeley segmentation bench-mark. The benchmark results show that the proposed segmentation al-gorithm produces segmentations comparable to those produced by the Normalised Cuts algorithm. 1

A lot of research towards global illumination has been focussed on the radiosity method. Nevertheless, it is still a rather academic topic which finds very slowly its way into commercial products. The scope of this tutorial is to describe recent developments in radiosity research that might narrow the gap with commercial applications. The first part of the tutorial course will be given by a pioneer in commercial computer graphics, who will set the stage for the demands of commercial rendering products and assess why radiosity has not been used until now.

model of top-down attentional control during visual

set of 13 categories of complex scenes. 1.

saliency. The system breaks down the complex problem of scene understanding by rapidly selecting, in a computationally efficient manner, conspicuous locations to be analyzed in detail. Index terms: Visual attention, scene analysis, feature extraction, target detection, visual search. \Pi I. Introduction

Abstract: This project pursues the development of a motion estimator allowing accurate visual estimates of egomotion and motion of independently moving objects. For this we propose the use of a feature based image representation containing two different types of visual entities, lines and junctions. Solving the problem of stereo and temporal matching, allows for motion estimation in image sequences. Furthermore, introducing methods for motion segmentation, using information collected from all pixels, allows the computation of motion estimates of independently objects, and disambiguates egomotion estimates.

This paper presents an algorithm and a software application for matching complex scenes in consumer image collections. By applying appropriate constraints to detected keypoint matches between a target and reference image, complex scenes from users ’ collections can be matched with very good