Lifting 3D Manhattan Lines from a Single Image

Srikumar Ramalingam, Matthew Brand; Proceedings of the IEEE International Conference on Computer Vision (ICCV), 2013, pp. 497-504


We propose a novel and an efficient method for reconstructing the 3D arrangement of lines extracted from a single image, using vanishing points, orthogonal structure, and an optimization procedure that considers all plausible connectivity constraints between lines. Line detection identifies a large number of salient lines that intersect or nearly intersect in an image, but relatively a few of these apparent junctions correspond to real intersections in the 3D scene. We use linear programming (LP) to identify a minimal set of least-violated connectivity constraints that are sufficient to unambiguously reconstruct the 3D lines. In contrast to prior solutions that primarily focused on well-behaved synthetic line drawings with severely restricting assumptions, we develop an algorithm that can work on real images. The algorithm produces line reconstruction by identifying 95% correct connectivity constraints in York Urban database, with a total computation time of 1 second per image.

Related Material

author = {Ramalingam, Srikumar and Brand, Matthew},
title = {Lifting 3D Manhattan Lines from a Single Image},
booktitle = {Proceedings of the IEEE International Conference on Computer Vision (ICCV)},
month = {December},
year = {2013}