This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. In most cases, these works may not be reposted without the explicit permission of the copyright holder.

Search for Publication

Year(s) from:  to 
Keywords (separated by spaces):

Superpixel Meshes for Fast Edge-Preserving Surface Reconstruction

András Bódis-Szomorú, Hayko Riemenschneider and Luc Van Gool
IEEE Conference on Computer Vision and Pattern Recognition (CVPR)


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.

Link to publisher's page
  author = {András Bódis-Szomorú 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)},
  year = {2015},
  keywords = {mesh, superpixel, 3D reconstruction, multi-view stereo, structure-from-motion, SfM}