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 ?tting 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:

Ó÷àñòíèêè

• Îëüãà Áàðèíîâà, Lomonosov Moscow State University
• Êîíóøèí À. Ñ., ÌÃÓ èì. Ëîìîíîñîâà
• Àíòîí ßêóáåíêî, ÌÃÓ èì. Ëîìîíîñîâà
• Âàäèì Êîíóøèí, Lomonosov Moscow State University

Ïóáëèêàöèè

• Barinova O, Konushin V, Yakubenko A, Lim H, Lee K, Konushin A. Fast automatic single-view 3-d reconstruction of urban scenes. Proceedings of European Conference of Computer Vision, 2008 (download)
• Barinova O, Kuzmishkina A, Vezhnevets A, Vezhnevets V. Learning class specific edges for vanishing point estimation. Graphicon, 2007 (download)

Áëàãîäàðíîñòè