Manhattan-World Stereo

Yasutaka Furukawa   Brian Curless   Steven M. Seitz
University of Washington

Richard Szeliski
Microsoft Research

Multi-view stereo (MVS) algorithms now produce reconstructions that rival laser range scanner accuracy. However, stereo algorithms require textured surfaces, and therefore work poorly for many architectural scenes (e.g., building interiors with textureless, painted alls).  This paper presents a novel MVS approach to overcome these limitations for Manhattan World scenes, i.e., scenes that consists of piece-wise planar surfaces with dominant directions. Given a set of calibrated photographs, we first reconstruct textured regions using an existing MVS algorithm, then extract dominant plane directions, generate plane hypotheses, and recover per-view depth maps using Markov random fields. We have tested our algorithm on several datasets ranging from office interiors to outdoor buildings, and demonstrate results that outperform the current state of the art for such texture-poor scenes.

Yasutaka Furukawa, Brian Curless, Steven M. Seitz, and Richard Szeliski.
Manhattan-World Stereo
CVPR 2009

Algorithm overview

Reconstructed depth maps (per-pixel plane information)

Video (comparison with a state-of-the-art multi-view stereo algorithm)

This work was supported in part by National Science Foundation grant IIS-0811878, the Office of Naval Research, the University of Washington Animation Research Labs, and Microsoft.

Contact: Yasutaka Furukawa

Last updated on 05/15/2009