Header logo is

Exploiting Object Similarity in 3D Reconstruction


Conference Paper



Despite recent progress, reconstructing outdoor scenes in 3D from movable platforms remains a highly difficult endeavor. Challenges include low frame rates, occlusions, large distortions and difficult lighting conditions. In this paper, we leverage the fact that the larger the reconstructed area, the more likely objects of similar type and shape will occur in the scene. This is particularly true for outdoor scenes where buildings and vehicles often suffer from missing texture or reflections, but share similarity in 3D shape. We take advantage of this shape similarity by locating objects using detectors and jointly reconstructing them while learning a volumetric model of their shape. This allows us to reduce noise while completing missing surfaces as objects of similar shape benefit from all observations for the respective category. We evaluate our approach with respect to LIDAR ground truth on a novel challenging suburban dataset and show its advantages over the state-of-the-art.

Author(s): Chen Zhou and Fatma Güney and Yizhou Wang and Andreas Geiger
Book Title: International Conference on Computer Vision (ICCV)
Year: 2015
Month: December

Department(s): Autonomous Vision, Perceiving Systems
Bibtex Type: Conference Paper (inproceedings)
Paper Type: Conference

Event Place: Santiago, Chile

State: Published

Links: pdf


  title = {Exploiting Object Similarity in 3D Reconstruction},
  author = {Zhou, Chen and G{\"u}ney, Fatma and Wang, Yizhou and Geiger, Andreas},
  booktitle = {International Conference on Computer Vision (ICCV)},
  month = dec,
  year = {2015},
  month_numeric = {12}