Header logo is avg

Learning Priors for Semantic 3D Reconstruction

2018

Conference Paper

avg


We present a novel semantic 3D reconstruction framework which embeds variational regularization into a neural network. Our network performs a fixed number of unrolled multi-scale optimization iterations with shared interaction weights. In contrast to existing variational methods for semantic 3D reconstruction, our model is end-to-end trainable and captures more complex dependencies between the semantic labels and the 3D geometry. Compared to previous learning-based approaches to 3D reconstruction, we integrate powerful long-range dependencies using variational coarse-to-fine optimization. As a result, our network architecture requires only a moderate number of parameters while keeping a high level of expressiveness which enables learning from very little data. Experiments on real and synthetic datasets demonstrate that our network achieves higher accuracy compared to a purely variational approach while at the same time requiring two orders of magnitude less iterations to converge. Moreover, our approach handles ten times more semantic class labels using the same computational resources.

Author(s): Ian Cherabier and Johannes Schönberger and Martin Oswald and Marc Pollefeys and Andreas Geiger
Book Title: European Conference on Computer Vision (ECCV)
Year: 2018
Month: September

Department(s): Autonomous Vision
Bibtex Type: Conference Paper (conference)

Event Place: Munich, Germany

Links: pdf
suppmat

BibTex

@conference{Cherabier2018ECCV,
  title = {Learning Priors for Semantic 3D Reconstruction },
  author = {Cherabier, Ian and Sch{\"o}nberger, Johannes and Oswald, Martin and Pollefeys, Marc and Geiger, Andreas},
  booktitle = {European Conference on Computer Vision (ECCV)},
  month = sep,
  year = {2018},
  month_numeric = {9}
}