Superpixel Meshes for Fast Edge-Preserving Surface Reconstruction

András Bódis-Szomorú
Hayko Riemenschneider
Luc Van Gool

IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 
Boston, MA, USA, 7-12 June 2015

Abstract

Multi-View-Stereo (MVS) methods aim for the highest detail possible, however, such detail is often not required. In this work, we propose a novel surface reconstruction method based on image edges, superpixels and second-order smoothness constraints, producing meshes comparable to classic MVS surfaces in quality but orders of magnitudes faster. Our method performs per-view dense depth optimization directly over sparse 3D Ground Control Points (GCPs), hence, removing the need for view pairing, image rectification, and stereo depth estimation, and allowing for full per-image parallelization. We use Structure-from-Motion (SfM) points as GCPs, but the method is not specific to these, e.g. LiDAR or RGB-D can also be used. The resulting meshes are compact and inherently edge-aligned with image gradients, enabling good-quality lightweight per-face flat renderings. Our experiments demonstrate on a variety of 3D datasets the superiority in speed and competitive surface quality.

Read

1-page Summary

Poster

Paper (8 pages)

Supplementary material (5 pages)

BibTeX

@inproceedings{BodisCVPR2015,
author =”Andr{\’a}s B{\’o}dis-Szomor{\’u} and Hayko Riemenschneider and Luc Van Gool”,
title =”Superpixel Meshes for Fast Edge-Preserving Surface Reconstruction”,
booktitle = “IEEE Conference on Computer Vision and Pattern Recognition (CVPR)”,
address = “Boston, MA, USA”, 
month =”7-12~June”,
year =”2015″,
}