Abstract

We propose a framework to automatically build 3D mod- els for scenes containing structures not amenable for photo-consistency based reconstruction due to having dynamic appearance. We analyze the dynamic appearance elements of a given scene by leveraging the imagery contained in Internet image photo-collections and online video sharing websites. Our approach combines large scale crowd sourced SfM techniques with image content segmentation and shape from silhouette techniques to build an iterative framework for 3D shape estimation. The developed system not only enables more complete and robust 3D model- ing, but it also enables more realistic visualizations through the identifi- cation of dynamic scene elements amenable to dynamic texture mapping. Experiments on crowd sourced image and video datasets illustrate the effectiveness of our automated data-driven approach.