Fast automatic single-view 3-d reconstruction of urban scenes

Contact person: Olga Barinova (obarinova@graphics.cs.msu.ru)

Overview

We consider the problem of estimating 3-d structure from a single still image of an outdoor urban scene. Our goal is to efficiently create 3-d models which are visually pleasant. We chose an appropriate 3-d model structure and formulate the task of 3-d reconstruction as model fitting problem. Our 3-d models are composed of a number of vertical walls and a ground plane, where ground-vertical boundary is a continuous polyline. We achieve computational efficiency by special preprocessing together with stepwise search of 3-d model parameters dividing the problem into two smaller sub-problems on chain graphs. The use of Conditional Random Field models for both problems allows to various cues. We infer orientation of vertical walls of 3-d model vanishing
points.

Images/Videos

Video below illustrates steps of the algorithm for 3-d modeling:

Team

Publications

Acknowledgements

We are grateful to Samsung Advanced Institute of Technology (SAIT) for financial support of this project.