Direkt zum Inhalt springen
Computer Vision Group
TUM Department of Informatics
Technical University of Munich

Technical University of Munich

Menu

Links


MonoRec: Semi-Supervised Dense Reconstruction in Dynamic Environments from a Single Moving Camera

Contact: Nan Yang, Lukas Von Stumberg, Niclas Zeller

[June 14., 2021] Code released! See below.



Code: https://github.com/Brummi/MonoRec

Abstract

In this paper, we propose MonoRec, a semi-supervised monocular dense reconstruction architecture that predicts depth maps from a single moving camera in dynamic environments. MonoRec is based on a multi-view stereo setting which encodes the information of multiple consecutive images in a cost volume. To deal with dynamic objects in the scene, we introduce a MaskModule that predicts moving object masks by leveraging the photometric inconsistencies encoded in the cost volumes. Unlike other multi-view stereo methods, MonoRec is able to predict accurate depths for both static and moving objects by leveraging the predicted masks. Furthermore, we present a novel multi-stage training scheme with a semi-supervised loss formulation that does not require LiDAR depth values. We carefully evaluate MonoRec on the KITTI dataset and show that it achieves state-of-the-art performance compared to both multi-view and single-view methods. With the model trained on KITTI, we further demonstrate that MonoRec is able to generalize well to both the Oxford RobotCar dataset and the more challenging TUM-Mono dataset recorded by a handheld camera.

Code

The source code of MonoRec has been released on GitHub under the flexible MIT License: https://github.com/Brummi/MonoRec.

Publications


Export as PDF, XML, TEX or BIB

Conference and Workshop Papers
2021
[]MonoRec: Semi-Supervised Dense Reconstruction in Dynamic Environments from a Single Moving Camera (F. Wimbauer, N. Yang, L. von Stumberg, N. Zeller and D Cremers), In IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2021. ([project page]) [bibtex] [arXiv:2011.11814]
2020
[]D3VO: Deep Depth, Deep Pose and Deep Uncertainty for Monocular Visual Odometry (N. Yang, L. von Stumberg, R. Wang and D. Cremers), In IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2020.  [bibtex] [arXiv:2003.01060] [pdf]Oral Presentation
2018
[]Deep Virtual Stereo Odometry: Leveraging Deep Depth Prediction for Monocular Direct Sparse Odometry (N. Yang, R. Wang, J. Stueckler and D. Cremers), In European Conference on Computer Vision (ECCV), 2018. ([arxiv],[supplementary],[project]) [bibtex]Oral Presentation
Powered by bibtexbrowser
Export as PDF, XML, TEX or BIB

Rechte Seite

Informatik IX
Chair of Computer Vision & Artificial Intelligence

Boltzmannstrasse 3
85748 Garching info@vision.in.tum.de

Follow us on:
CVG Group DVL Group

News

03.04.2022

In April 2022 Jürgen Sturm, Christian Kerl and Daniel Cremers were featured among the top 10 most influential scholars in robotics of the last decade.

31.03.2022

We have open PhD and postdoc positions! To apply, please use our application form.

08.03.2022

We have six papers accepted to CVPR 2022 in New Orleans!

31.01.2022

We have two papers accepted to ICRA 2022 - congrats to Lukas von Stumberg, Qing Cheng and Niclas Zeller!

05.12.2021
More