DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction

Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer

Publikation: Beitrag in Buch/Bericht/KonferenzbandBeitrag in einem KonferenzbandBegutachtung

Abstract

Deep Neural Networks (DNNs) have the potential to improve the quality of image-based 3D reconstructions. However, the use of DNNs in the context of 3D reconstruction from large and high-resolution image datasets is still an open challenge, due to memory and computational constraints. We propose a pipeline which takes advantage of DNNs to improve the quality of 3D reconstructions while being able to handle large and high-resolution datasets. In particular, we propose a confidence prediction network explicitly tailored for Multi-View Stereo (MVS) and we use it for both depth map outlier filtering and depth map refinement within our pipeline, in order to improve the quality of the final 3D reconstructions. We train our confidence prediction network on (semi-)dense ground truth depth maps from publicly available real world MVS datasets. With extensive experiments on popular benchmarks, we show that our overall pipeline can produce state-of-the-art 3D reconstructions, both qualitatively and quantitatively.

Originalspracheenglisch
TitelProceedings - 2020 International Conference on 3D Vision, 3DV 2020
Herausgeber (Verlag)IEEEXplore
Seiten404-413
Seitenumfang10
ISBN (elektronisch)9781728181288
DOIs
PublikationsstatusVeröffentlicht - 25 Nov. 2020
VeranstaltungInternational Virtual Conference on 3D Vision: 3DV 2020 - Online, Fukuoka, Virtual, Japan
Dauer: 25 Nov. 202028 Nov. 2020
http://3dv2020.dgcv.nii.ac.jp

Publikationsreihe

NameProceedings - 2020 International Conference on 3D Vision, 3DV 2020

Konferenz

KonferenzInternational Virtual Conference on 3D Vision
Kurztitel3DV
Land/GebietJapan
OrtFukuoka, Virtual
Zeitraum25/11/2028/11/20
Internetadresse

ASJC Scopus subject areas

  • Artificial intelligence
  • Maschinelles Sehen und Mustererkennung

Fingerprint

Untersuchen Sie die Forschungsthemen von „DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction“. Zusammen bilden sie einen einzigartigen Fingerprint.

Dieses zitieren