Parameterization of Ambiguity in Monocular Depth Prediction

Patrik Persson, Linn Ostrom, Carl Olsson, Kalle Astrom

Research output: Chapter in Book/Report/Conference proceedingPaper in conference proceedingpeer-review

Abstract

Monocular depth estimation is a highly challenging problem that is often addressed with deep neural networks. While these use recognition of high level image features to predict reasonably looking depth maps,the result often has poor metric accuracy. Moreover,the standard feed forward architecture does not allow modification of the prediction based on cues other than the image.In this paper we relax the monocular depth estimation task by proposing a network that allows us to complement image features with a set of auxiliary variables. These allow disambiguation when image features are not enough to accurately pinpoint the exact depth map and can be thought of as a low dimensional parameterization of the surfaces that are reasonable monocular predictions. By searching the parameterization we can combine monocular estimation with traditional photoconsistency or geometry based methods to achieve both visually appealing and metrically accurate surface estimations. Since we relax the problem we are able to work with smaller networks than current architectures. In addition we design a self-supervised training scheme,eliminating the need for ground truth image depth-map pairs. Our experimental evaluation shows that our method generates more accurate depth maps and generalizes better than competing state-of-the-art approaches.

Original languageEnglish
Title of host publicationProceedings - 2021 International Conference on 3D Vision, 3DV 2021
PublisherIEEE - Institute of Electrical and Electronics Engineers Inc.
Pages761-770
Number of pages10
ISBN (Electronic)9781665426886
DOIs
Publication statusPublished - 2021
Event9th International Conference on 3D Vision, 3DV 2021 - Virtual, Online, United Kingdom
Duration: 2021 Dec 12021 Dec 3

Conference

Conference9th International Conference on 3D Vision, 3DV 2021
Country/TerritoryUnited Kingdom
CityVirtual, Online
Period2021/12/012021/12/03

Subject classification (UKÄ)

  • Computer Vision and Robotics (Autonomous Systems)

Free keywords

  • 3D Reconstruction
  • Machine Learning
  • Monocular Depth Parameterization

Fingerprint

Dive into the research topics of 'Parameterization of Ambiguity in Monocular Depth Prediction'. Together they form a unique fingerprint.

Cite this