LCR-SMPL: Toward Real-Time Human Detection and 3D Reconstruction from a Single RGB Image

Elena Pena-Tapia; Ryo Hachiuma; Antoine Pasquali; Hideo Saito

doi:10.1109/ISMAR-Adjunct51615.2020.00062

LCR-SMPL: Toward Real-Time Human Detection and 3D Reconstruction from a Single RGB Image

Elena Pena-Tapia, Ryo Hachiuma, Antoine Pasquali, Hideo Saito

Department of Information and Computer Science

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

This paper presents a novel method for simultaneous human detection and 3D shape reconstruction from a single RGB image. It offers a low-cost alternative to existing motion capture solutions, allowing to reconstruct realistic human 3D shapes and poses by leveraging the speed of an object-detection based architecture and the extended applicability of a parametric human mesh model. Evaluation results using a synthetic dataset show that our approach is on-par with conventional 3D reconstruction methods in terms of accuracy, and outperforms them in terms of inference speed, particularly in the case of multi-person images.

Original language	English
Title of host publication	Adjunct Proceedings of the 2020 IEEE International Symposium on Mixed and Augmented Reality, ISMAR-Adjunct 2020
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	211-212
Number of pages	2
ISBN (Electronic)	9781728176758
DOIs	https://doi.org/10.1109/ISMAR-Adjunct51615.2020.00062
Publication status	Published - 2020 Nov
Event	2020 IEEE International Symposium on Mixed and Augmented Reality, ISMAR-Adjunct 2020 - Virtual, Recife, Brazil Duration: 2020 Nov 9 → 2020 Nov 13

Publication series

Name	Adjunct Proceedings of the 2020 IEEE International Symposium on Mixed and Augmented Reality, ISMAR-Adjunct 2020

Conference

Conference	2020 IEEE International Symposium on Mixed and Augmented Reality, ISMAR-Adjunct 2020
Country/Territory	Brazil
City	Virtual, Recife
Period	20/11/9 → 20/11/13

Keywords

Artificial Intelligence
Artificial Intelligence
Computer vision
Computer vision
Computer vision problems
Computer vision problems
Reconstruction
Shape inference

ASJC Scopus subject areas

Computer Science Applications
Media Technology
Modelling and Simulation

Access to Document

10.1109/ISMAR-Adjunct51615.2020.00062

Cite this

Pena-Tapia, E., Hachiuma, R., Pasquali, A., & Saito, H. (2020). LCR-SMPL: Toward Real-Time Human Detection and 3D Reconstruction from a Single RGB Image. In Adjunct Proceedings of the 2020 IEEE International Symposium on Mixed and Augmented Reality, ISMAR-Adjunct 2020 (pp. 211-212). [9288458] (Adjunct Proceedings of the 2020 IEEE International Symposium on Mixed and Augmented Reality, ISMAR-Adjunct 2020). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ISMAR-Adjunct51615.2020.00062

LCR-SMPL: Toward Real-Time Human Detection and 3D Reconstruction from a Single RGB Image. / Pena-Tapia, Elena; Hachiuma, Ryo; Pasquali, Antoine et al.
Adjunct Proceedings of the 2020 IEEE International Symposium on Mixed and Augmented Reality, ISMAR-Adjunct 2020. Institute of Electrical and Electronics Engineers Inc., 2020. p. 211-212 9288458 (Adjunct Proceedings of the 2020 IEEE International Symposium on Mixed and Augmented Reality, ISMAR-Adjunct 2020).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Pena-Tapia, E, Hachiuma, R, Pasquali, A & Saito, H 2020, LCR-SMPL: Toward Real-Time Human Detection and 3D Reconstruction from a Single RGB Image. in Adjunct Proceedings of the 2020 IEEE International Symposium on Mixed and Augmented Reality, ISMAR-Adjunct 2020., 9288458, Adjunct Proceedings of the 2020 IEEE International Symposium on Mixed and Augmented Reality, ISMAR-Adjunct 2020, Institute of Electrical and Electronics Engineers Inc., pp. 211-212, 2020 IEEE International Symposium on Mixed and Augmented Reality, ISMAR-Adjunct 2020, Virtual, Recife, Brazil, 20/11/9. https://doi.org/10.1109/ISMAR-Adjunct51615.2020.00062

Pena-Tapia E, Hachiuma R, Pasquali A, Saito H. LCR-SMPL: Toward Real-Time Human Detection and 3D Reconstruction from a Single RGB Image. In Adjunct Proceedings of the 2020 IEEE International Symposium on Mixed and Augmented Reality, ISMAR-Adjunct 2020. Institute of Electrical and Electronics Engineers Inc. 2020. p. 211-212. 9288458. (Adjunct Proceedings of the 2020 IEEE International Symposium on Mixed and Augmented Reality, ISMAR-Adjunct 2020). doi: 10.1109/ISMAR-Adjunct51615.2020.00062

Pena-Tapia, Elena ; Hachiuma, Ryo ; Pasquali, Antoine et al. / LCR-SMPL : Toward Real-Time Human Detection and 3D Reconstruction from a Single RGB Image. Adjunct Proceedings of the 2020 IEEE International Symposium on Mixed and Augmented Reality, ISMAR-Adjunct 2020. Institute of Electrical and Electronics Engineers Inc., 2020. pp. 211-212 (Adjunct Proceedings of the 2020 IEEE International Symposium on Mixed and Augmented Reality, ISMAR-Adjunct 2020).

@inproceedings{5e23964929d94e919e91b3717f12b74e,

title = "LCR-SMPL: Toward Real-Time Human Detection and 3D Reconstruction from a Single RGB Image",

abstract = "This paper presents a novel method for simultaneous human detection and 3D shape reconstruction from a single RGB image. It offers a low-cost alternative to existing motion capture solutions, allowing to reconstruct realistic human 3D shapes and poses by leveraging the speed of an object-detection based architecture and the extended applicability of a parametric human mesh model. Evaluation results using a synthetic dataset show that our approach is on-par with conventional 3D reconstruction methods in terms of accuracy, and outperforms them in terms of inference speed, particularly in the case of multi-person images.",

keywords = "Artificial Intelligence, Artificial Intelligence, Computer vision, Computer vision, Computer vision problems, Computer vision problems, Reconstruction, Shape inference",

author = "Elena Pena-Tapia and Ryo Hachiuma and Antoine Pasquali and Hideo Saito",

note = "Publisher Copyright: {\textcopyright} 2020 IEEE.; 2020 IEEE International Symposium on Mixed and Augmented Reality, ISMAR-Adjunct 2020 ; Conference date: 09-11-2020 Through 13-11-2020",

year = "2020",

month = nov,

doi = "10.1109/ISMAR-Adjunct51615.2020.00062",

language = "English",

series = "Adjunct Proceedings of the 2020 IEEE International Symposium on Mixed and Augmented Reality, ISMAR-Adjunct 2020",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "211--212",

booktitle = "Adjunct Proceedings of the 2020 IEEE International Symposium on Mixed and Augmented Reality, ISMAR-Adjunct 2020",

}

TY - GEN

T1 - LCR-SMPL

T2 - 2020 IEEE International Symposium on Mixed and Augmented Reality, ISMAR-Adjunct 2020

AU - Pena-Tapia, Elena

AU - Hachiuma, Ryo

AU - Pasquali, Antoine

AU - Saito, Hideo

PY - 2020/11

Y1 - 2020/11

N2 - This paper presents a novel method for simultaneous human detection and 3D shape reconstruction from a single RGB image. It offers a low-cost alternative to existing motion capture solutions, allowing to reconstruct realistic human 3D shapes and poses by leveraging the speed of an object-detection based architecture and the extended applicability of a parametric human mesh model. Evaluation results using a synthetic dataset show that our approach is on-par with conventional 3D reconstruction methods in terms of accuracy, and outperforms them in terms of inference speed, particularly in the case of multi-person images.

AB - This paper presents a novel method for simultaneous human detection and 3D shape reconstruction from a single RGB image. It offers a low-cost alternative to existing motion capture solutions, allowing to reconstruct realistic human 3D shapes and poses by leveraging the speed of an object-detection based architecture and the extended applicability of a parametric human mesh model. Evaluation results using a synthetic dataset show that our approach is on-par with conventional 3D reconstruction methods in terms of accuracy, and outperforms them in terms of inference speed, particularly in the case of multi-person images.

KW - Artificial Intelligence

KW - Computer vision

KW - Computer vision problems

KW - Reconstruction

KW - Shape inference

UR - http://www.scopus.com/inward/record.url?scp=85099589460&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85099589460&partnerID=8YFLogxK

U2 - 10.1109/ISMAR-Adjunct51615.2020.00062

DO - 10.1109/ISMAR-Adjunct51615.2020.00062

M3 - Conference contribution

AN - SCOPUS:85099589460

T3 - Adjunct Proceedings of the 2020 IEEE International Symposium on Mixed and Augmented Reality, ISMAR-Adjunct 2020

SP - 211

EP - 212

BT - Adjunct Proceedings of the 2020 IEEE International Symposium on Mixed and Augmented Reality, ISMAR-Adjunct 2020

PB - Institute of Electrical and Electronics Engineers Inc.

Y2 - 9 November 2020 through 13 November 2020

ER -

LCR-SMPL: Toward Real-Time Human Detection and 3D Reconstruction from a Single RGB Image

Abstract

Publication series

Conference

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this