Header logo is avg

RayNet: Learning Volumetric 3D Reconstruction with Ray Potentials


Conference Paper


In this paper, we consider the problem of reconstructing a dense 3D model using images captured from different views. Recent methods based on convolutional neural networks (CNN) allow learning the entire task from data. However, they do not incorporate the physics of image formation such as perspective geometry and occlusion. Instead, classical approaches based on Markov Random Fields (MRF) with ray-potentials explicitly model these physical processes, but they cannot cope with large surface appearance variations across different viewpoints. In this paper, we propose RayNet, which combines the strengths of both frameworks. RayNet integrates a CNN that learns view-invariant feature representations with an MRF that explicitly encodes the physics of perspective projection and occlusion. We train RayNet end-to-end using empirical risk minimization. We thoroughly evaluate our approach on challenging real-world datasets and demonstrate its benefits over a piece-wise trained baseline, hand-crafted models as well as other learning-based approaches.

Author(s): Despoina Paschalidou and Ali Osman Ulusoy and Carolin Schmitt and Luc Gool and Andreas Geiger
Book Title: IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
Year: 2018
Publisher: IEEE Computer Society

Department(s): Autonomous Vision
Research Project(s): RayNet
Bibtex Type: Conference Paper (inproceedings)
Paper Type: Conference

Event Name: IEEE International Conference on Computer Vision and Pattern Recognition (CVPR) 2018
Event Place: Salt Lake City, USA

Links: pdf
Project Page


  title = {RayNet: Learning Volumetric 3D Reconstruction with Ray Potentials},
  author = {Paschalidou, Despoina and Ulusoy, Ali Osman and Schmitt, Carolin and Gool, Luc and Geiger, Andreas},
  booktitle = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
  publisher = {IEEE Computer Society},
  year = {2018}