High-level, or holistic, scene understanding involves
reasoning about objects, regions, and the 3D relationships
between them. This requires a representation above the
level of ...
This paper presents a new method for segmentation of images into large regions that reflect the real world objects present in a scene. It explores the feasibility of utilizing sp...
In this paper we introduce a relighting algorithm for diffuse outdoor scenes that enables us to create geometrically correct and illumination consistent models from a series of ra...
Abstract. In this paper, we describe an unsupervised learning framework to segment a scene into semantic regions and to build semantic scene models from longterm observations of mo...
We present a new approach for activity modelling and anomaly detection based on non-parametric Gaussian Process (GP) models. Specifically, GP regression models are formulated to l...