Learning Lightprobes for Mixed Reality Illumination

David Mandl, Kwang Moo Yi, Peter Mohr-Ziak, Peter M. Roth, Pascal Fua, Vincent Lepetit, Dieter Schmalstieg, Denis Kalkofen

Publikation: KonferenzbeitragPaperForschungBegutachtung

Abstract

This paper presents the first photometric registration pipeline for
Mixed Reality based on high quality illumination estimation using
convolutional neural networks (CNNs). For easy adaptation and deployment
of the system, we train the CNNs using purely synthetic
images and apply them to real image data. To keep the pipeline accurate
and efficient, we propose to fuse the light estimation results
from multiple CNN instances and show an approach for caching
estimates over time. For optimal performance, we furthermore explore
multiple strategies for the CNN training. Experimental results
show that the proposed method yields highly accurate estimates for
photo-realistic augmentations.
Originalspracheenglisch
Seitenumfang8
DOIs
PublikationsstatusVeröffentlicht - 9 Okt 2017
VeranstaltungInternational Symposium on Mixed and Augmented
Reality 2017
- La Cité, Nantes, Frankreich
Dauer: 9 Okt 201713 Okt 2017
https://ismar2017.sciencesconf.org/

Konferenz

KonferenzInternational Symposium on Mixed and Augmented
Reality 2017
KurztitelISMAR 2017
LandFrankreich
OrtNantes
Zeitraum9/10/1713/10/17
Internetadresse

Fingerprint

Pipelines
Lighting
Electric fuses
Neural networks

Dies zitieren

Mandl, D., Yi, K. M., Mohr-Ziak, P., Roth, P. M., Fua, P., Lepetit, V., ... Kalkofen, D. (2017). Learning Lightprobes for Mixed Reality Illumination. Beitrag in International Symposium on Mixed and Augmented
Reality 2017, Nantes, Frankreich. https://doi.org/10.1109/ISMAR.2017.25

Learning Lightprobes for Mixed Reality Illumination. / Mandl, David; Yi, Kwang Moo; Mohr-Ziak, Peter; Roth, Peter M.; Fua, Pascal; Lepetit, Vincent; Schmalstieg, Dieter; Kalkofen, Denis.

2017. Beitrag in International Symposium on Mixed and Augmented
Reality 2017, Nantes, Frankreich.

Publikation: KonferenzbeitragPaperForschungBegutachtung

Mandl D, Yi KM, Mohr-Ziak P, Roth PM, Fua P, Lepetit V et al. Learning Lightprobes for Mixed Reality Illumination. 2017. Beitrag in International Symposium on Mixed and Augmented
Reality 2017, Nantes, Frankreich. https://doi.org/10.1109/ISMAR.2017.25
Mandl, David ; Yi, Kwang Moo ; Mohr-Ziak, Peter ; Roth, Peter M. ; Fua, Pascal ; Lepetit, Vincent ; Schmalstieg, Dieter ; Kalkofen, Denis. / Learning Lightprobes for Mixed Reality Illumination. Beitrag in International Symposium on Mixed and Augmented
Reality 2017, Nantes, Frankreich.8 S.
@conference{43fc66b5266d429c8cbe8c24f5401140,
title = "Learning Lightprobes for Mixed Reality Illumination",
abstract = "This paper presents the first photometric registration pipeline forMixed Reality based on high quality illumination estimation usingconvolutional neural networks (CNNs). For easy adaptation and deploymentof the system, we train the CNNs using purely syntheticimages and apply them to real image data. To keep the pipeline accurateand efficient, we propose to fuse the light estimation resultsfrom multiple CNN instances and show an approach for cachingestimates over time. For optimal performance, we furthermore exploremultiple strategies for the CNN training. Experimental resultsshow that the proposed method yields highly accurate estimates forphoto-realistic augmentations.",
author = "David Mandl and Yi, {Kwang Moo} and Peter Mohr-Ziak and Roth, {Peter M.} and Pascal Fua and Vincent Lepetit and Dieter Schmalstieg and Denis Kalkofen",
year = "2017",
month = "10",
day = "9",
doi = "10.1109/ISMAR.2017.25",
language = "English",
note = "International Symposium on Mixed and Augmented<br/>Reality 2017, ISMAR 2017 ; Conference date: 09-10-2017 Through 13-10-2017",
url = "https://ismar2017.sciencesconf.org/",

}

TY - CONF

T1 - Learning Lightprobes for Mixed Reality Illumination

AU - Mandl, David

AU - Yi, Kwang Moo

AU - Mohr-Ziak, Peter

AU - Roth, Peter M.

AU - Fua, Pascal

AU - Lepetit, Vincent

AU - Schmalstieg, Dieter

AU - Kalkofen, Denis

PY - 2017/10/9

Y1 - 2017/10/9

N2 - This paper presents the first photometric registration pipeline forMixed Reality based on high quality illumination estimation usingconvolutional neural networks (CNNs). For easy adaptation and deploymentof the system, we train the CNNs using purely syntheticimages and apply them to real image data. To keep the pipeline accurateand efficient, we propose to fuse the light estimation resultsfrom multiple CNN instances and show an approach for cachingestimates over time. For optimal performance, we furthermore exploremultiple strategies for the CNN training. Experimental resultsshow that the proposed method yields highly accurate estimates forphoto-realistic augmentations.

AB - This paper presents the first photometric registration pipeline forMixed Reality based on high quality illumination estimation usingconvolutional neural networks (CNNs). For easy adaptation and deploymentof the system, we train the CNNs using purely syntheticimages and apply them to real image data. To keep the pipeline accurateand efficient, we propose to fuse the light estimation resultsfrom multiple CNN instances and show an approach for cachingestimates over time. For optimal performance, we furthermore exploremultiple strategies for the CNN training. Experimental resultsshow that the proposed method yields highly accurate estimates forphoto-realistic augmentations.

U2 - 10.1109/ISMAR.2017.25

DO - 10.1109/ISMAR.2017.25

M3 - Paper

ER -