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

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

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	2025 Conference on Lasers and Electro-Optics, CLEO 2025
ISBN (Electronic)	9781957171500
State	Published - 2025
Event	2025 Conference on Lasers and Electro-Optics, CLEO 2025 - Long Beach, United States Duration: 4 May 2025 → 9 May 2025

Publication series

Name	2025 Conference on Lasers and Electro-Optics, CLEO 2025

Conference

Conference	2025 Conference on Lasers and Electro-Optics, CLEO 2025
Country/Territory	United States
City	Long Beach
Period	4/05/25 → 9/05/25

Cite this

@inproceedings{b914c78ee01d44e9a49d3766da661c7c,

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} 2025 Optica.; 2025 Conference on Lasers and Electro-Optics, CLEO 2025 ; Conference date: 04-05-2025 Through 09-05-2025",

year = "2025",

language = "English",

series = "2025 Conference on Lasers and Electro-Optics, CLEO 2025",

booktitle = "2025 Conference on Lasers and Electro-Optics, CLEO 2025",

}

Video Physics-Informed Masked Autoencoder for High-Speed Single-Photon Imaging of Dynamic 3D Scenes. / McEvoy, Luke; Tafone, Daniel; Sua, Yong Meng et al.
2025 Conference on Lasers and Electro-Optics, CLEO 2025. 2025. (2025 Conference on Lasers and Electro-Optics, 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/105021465238

UR - https://www.scopus.com/pages/publications/105021465238#tab=citedBy

M3 - Conference contribution

AN - SCOPUS:105021465238

T3 - 2025 Conference on Lasers and Electro-Optics, CLEO 2025

BT - 2025 Conference on Lasers and Electro-Optics, CLEO 2025

T2 - 2025 Conference on Lasers and Electro-Optics, CLEO 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

Other files and links

Fingerprint

Cite this