Live Action Data Input and Output

Informazioni relative al progetto

LADIO

ID dell’accordo di sovvenzione: 731970

DOI

10.3030/731970

Progetto chiuso

Data della firma CE 10 Ottobre 2016

Data di avvio 1 Dicembre 2016

Data di completamento 31 Agosto 2018

Finanziato da

• INDUSTRIAL LEADERSHIP - Leadership in enabling and industrial technologies - Information and Communication Technologies (ICT)

Costo totale

€ 1 213 753,63

Contributo UE

€ 1 051 422,70

Coordinato da

SIMULA RESEARCH LABORATORY AS
Norway

CORDIS fornisce collegamenti ai risultati finali pubblici e alle pubblicazioni dei progetti ORIZZONTE.

I link ai risultati e alle pubblicazioni dei progetti del 7° PQ, così come i link ad alcuni tipi di risultati specifici come dataset e software, sono recuperati dinamicamente da .OpenAIRE .

Risultati finali

Other (15)

File format implementations verified in LADIO prototypes
Lens calibration from 3D Reconstruction

Implement lens calibration from 3D Reconstruction in openMVG

GPU optimised version of OpenCMPMVS

Implement GPU optimised version of OpenCMPMVS

CamBox and MiniBox

RT Acquisition - Implementation of the CamBox and MiniBox

Improve SfM accuracy and precision
SetBox

SetBox - Implementation of the SetBox

File formats release implementations as open source

Release implementations as open source

SfM LiDAR integration

SfM: LiDAR integration

SfM integration for 360° cameras and camera rigs
LADIO Application importers and exporters

Implement LADIO Application importers and exporters

Implement SfM Multibody into openMVG
Backend Timeline Module

Implement Backend Timeline Module

OpenCMPMVS

Implement OpenCMPMVS

Advanced OpenCMPMVS - Multibody and LiDAR

Implement advanced OpenCMPMVS - Multibody and LiDAR

Distributed Network

Implementation of the Distributed Data Management system

Documents, reports (9)

Technical mechanisms for Management

Documentation of the deployed technical mechanisms

Report on Pilot Production
Final report

Final project report

Quarterly management reports 1 and 2
Quarterly management reports 3 and 4
3D Reconstruction benchmarks with dataset

Deliver 3D Reconstruction benchmarks with dataset

Model & API definition

Documentation of extensions for EBU CCDN, EBUCore and newly defined REST API

Quarterly management reports 5 and 6
File and database formats for data storage

List of file formats to use unchanged and recommendation for filling gaps

Open Research Data Pilot (1)

Data Management Plan

The LADIO project participates in the pilot on open research data. In this task we will formulate a data management plan to make available data sets that can benefit the academic community and other users.

Pubblicazioni

Conference proceedings (5)

On the Two-View Geometry of Unsynchronized Cameras

Autori: Cenek Albl, Zuzana Kukelova, Andrew Fitzgibbon, Jan Heller, Matej Smid, Tomas Pajdla
Pubblicato in: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017, Pagina/e 5593-5602, ISBN 978-1-5386-0457-1
Editore: IEEE
DOI: 10.1109/CVPR.2017.593

Uncertainty Computation in Large 3D Reconstruction

Autori: Michal Polic, Tomas Pajdla
Pubblicato in: Scandinavian Conference on Image Analysis, 2017, Pagina/e 110-121, ISBN 978-3-319-59126-1
Editore: Springer International Publishing
DOI: 10.1007/978-3-319-59126-1_10

Towards multi-scale feature detection repeatable over intensity and depth images

Autori: Hatem A. Rashwan, Sylvie Chambon, Pierre Gurdjos, Geraldine Morin, Vincent Charvillat
Pubblicato in: 2016 IEEE International Conference on Image Processing (ICIP), 2016, Pagina/e 36-40, ISBN 978-1-4673-9961-6
Editore: IEEE
DOI: 10.1109/ICIP.2016.7532314

Are Large-Scale 3D Models Really Necessary for Accurate Visual Localization?

Autori: Torsten Sattler, Akihiko Torii, Josef Sivic, Marc Pollefeys, Hajime Taira, Masatoshi Okutomi, Tomas Pajdla
Pubblicato in: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017, Pagina/e 6175-6184, ISBN 978-1-5386-0457-1
Editore: IEEE
DOI: 10.1109/CVPR.2017.654

Towards Recognizing of 3D Models Using A Single Image

Autori: Rashwan, Hatem A.; Chambon, Sylvie; Morin, Geraldine; Gurdjos, Pierre; Charvillat, Vincent
Pubblicato in: Eurographics Workshop on 3D Object Retrieval, 2017, ISBN 978-3-03868-030-7
Editore: The Eurographics Association
DOI: 10.2312/3dor.20171062

Peer reviewed articles (3)

Selecting image pairs for SfM by introducing Jaccard Similarity

Autori: Takaharu Kato, Ikuko Shimizu, Tomas Pajdla
Pubblicato in: IPSJ Transactions on Computer Vision and Applications, Numero 9/1, 2017, ISSN 1882-6695
Editore: Information Processing Society of Japan
DOI: 10.1186/s41074-017-0021-8

Distortion Varieties

Autori: Joe Kileel, Zuzana Kukelova, Tomas Pajdla, Bernd Sturmfels
Pubblicato in: Foundations of Computational Mathematics, 2017, ISSN 1615-3375
Editore: Springer Verlag
DOI: 10.1007/s10208-017-9361-0

24/7 Place Recognition by View Synthesis

Autori: Akihiko Torii, Relja Arandjelovic, Josef Sivic, Masatoshi Okutomi, Tomas Pajdla
Pubblicato in: IEEE Transactions on Pattern Analysis and Machine Intelligence, Numero 40/2, 2018, Pagina/e 257-271, ISSN 0162-8828
Editore: Institute of Electrical and Electronics Engineers
DOI: 10.1109/TPAMI.2017.2667665