Abstract

This paper describes an approach to reconstruct the com- plete history of a 3-d scene over time from imagery. The proposed ap- proach avoids rebuilding 3-d models of the scene at each time instant. Instead, the approach employs an initial 3-d model which is continuously updated with changes in the environment to form a full 4-d representa- tion. This updating scheme is enabled by a novel algorithm that infers 3-d changes with respect to the model at one time step from images taken at a subsequent time step. This algorithm can effectively detect changes even when the illumination conditions between image collections are significantly different. The performance of the proposed framework is demonstrated on four challenging datasets in terms of 4-d modeling accuracy as well as quantitative evaluation of 3-d change detection.