Video Physics-Informed Masked Autoencoder for High-Speed Single-Photon Imaging of Dynamic 3D scenes

Luke McEvoy; Daniel Tafone; Yong Meng Sua; Yuping Huang

doi:10.1364/cleo_at.2025.aa133_5

Video Physics-Informed Masked Autoencoder for High-Speed Single-Photon Imaging of Dynamic 3D scenes

Luke McEvoy
, Daniel Tafone
, Yong Meng Sua
, Yuping Huang

Department of Physics

Stevens Institute of Technology

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

Abstract

We perform single-photon imaging of dynamic 3D scenes 50x faster than traditional systems using a 98% mask. We then reconstruct with minimal deviation from ground truth through our Video Physics-Informed Masked Autoencoder (VideoPIMAE) model architecture.

Original language	English
Title of host publication	CLEO
Subtitle of host publication	Applications and Technology - Proceedings CLEO 2025
ISBN (Electronic)	9781957171500
DOIs	https://doi.org/10.1364/cleo_at.2025.aa133_5
State	Published - 2025
Event	2025 CLEO: Applications and Technology, CLEO-AT 2025 - Long Beach, United States Duration: 4 May 2025 → 9 May 2025

Publication series

Name	CLEO: Applications and Technology - Proceedings CLEO 2025

Conference

Conference	2025 CLEO: Applications and Technology, CLEO-AT 2025
Country/Territory	United States
City	Long Beach
Period	4/05/25 → 9/05/25

Access to Document

10.1364/cleo_at.2025.aa133_5

Cite this

@inproceedings{671702ad21764d518479db4dd734ada0,

title = "Video Physics-Informed Masked Autoencoder for High-Speed Single-Photon Imaging of Dynamic 3D scenes",

abstract = "We perform single-photon imaging of dynamic 3D scenes 50x faster than traditional systems using a 98\% mask. We then reconstruct with minimal deviation from ground truth through our Video Physics-Informed Masked Autoencoder (VideoPIMAE) model architecture.",

author = "Luke McEvoy and Daniel Tafone and Sua, \{Yong Meng\} and Yuping Huang",

note = "Publisher Copyright: {\textcopyright} Optica Publishing Group 2025 {\textcopyright} 2024 The Author(s); 2025 CLEO: Applications and Technology, CLEO-AT 2025 ; Conference date: 04-05-2025 Through 09-05-2025",

year = "2025",

doi = "10.1364/cleo\_at.2025.aa133\_5",

language = "English",

series = "CLEO: Applications and Technology - Proceedings CLEO 2025",

booktitle = "CLEO",

}

McEvoy, L, Tafone, D, Sua, YM & Huang, Y 2025, Video Physics-Informed Masked Autoencoder for High-Speed Single-Photon Imaging of Dynamic 3D scenes. in CLEO: Applications and Technology - Proceedings CLEO 2025. CLEO: Applications and Technology - Proceedings CLEO 2025, 2025 CLEO: Applications and Technology, CLEO-AT 2025, Long Beach, United States, 4/05/25. https://doi.org/10.1364/cleo_at.2025.aa133_5

Video Physics-Informed Masked Autoencoder for High-Speed Single-Photon Imaging of Dynamic 3D scenes. / McEvoy, Luke; Tafone, Daniel; Sua, Yong Meng et al.
CLEO: Applications and Technology - Proceedings CLEO 2025. 2025. (CLEO: Applications and Technology - Proceedings CLEO 2025).

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

TY - GEN

T1 - Video Physics-Informed Masked Autoencoder for High-Speed Single-Photon Imaging of Dynamic 3D scenes

AU - McEvoy, Luke

AU - Tafone, Daniel

AU - Sua, Yong Meng

AU - Huang, Yuping

PY - 2025

Y1 - 2025

N2 - We perform single-photon imaging of dynamic 3D scenes 50x faster than traditional systems using a 98% mask. We then reconstruct with minimal deviation from ground truth through our Video Physics-Informed Masked Autoencoder (VideoPIMAE) model architecture.

AB - We perform single-photon imaging of dynamic 3D scenes 50x faster than traditional systems using a 98% mask. We then reconstruct with minimal deviation from ground truth through our Video Physics-Informed Masked Autoencoder (VideoPIMAE) model architecture.

UR - https://www.scopus.com/pages/publications/105033339291

UR - https://www.scopus.com/pages/publications/105033339291#tab=citedBy

U2 - 10.1364/cleo_at.2025.aa133_5

DO - 10.1364/cleo_at.2025.aa133_5

M3 - Conference contribution

AN - SCOPUS:105033339291

T3 - CLEO: Applications and Technology - Proceedings CLEO 2025

BT - CLEO

T2 - 2025 CLEO: Applications and Technology, CLEO-AT 2025

Y2 - 4 May 2025 through 9 May 2025

ER -

Video Physics-Informed Masked Autoencoder for High-Speed Single-Photon Imaging of Dynamic 3D scenes

Abstract

Publication series

Conference

Access to Document

Other files and links

Fingerprint

Cite this