Disambiguating Monocular Depth Estimation with a Single Transient

Mark Nishimura; David B. Lindell; Christopher A. Metzler; Gordon Wetzstein

doi:10.1007/978-3-030-58589-1_9

Disambiguating Monocular Depth Estimation with a Single Transient

Mark Nishimura, David B. Lindell, Christopher A. Metzler, Gordon Wetzstein

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

12 Scopus citations

Abstract

Monocular depth estimation algorithms successfully predict the relative depth order of objects in a scene. However, because of the fundamental scale ambiguity associated with monocular images, these algorithms fail at correctly predicting true metric depth. In this work, we demonstrate how a depth histogram of the scene, which can be readily captured using a single-pixel time-resolved detector, can be fused with the output of existing monocular depth estimation algorithms to resolve the depth ambiguity problem. We validate this novel sensor fusion technique experimentally and in extensive simulation. We show that it significantly improves the performance of several state-of-the-art monocular depth estimation algorithms.

Original language	English (US)
Title of host publication	Computer Vision – ECCV 2020
Publisher	Springer International Publishing
Pages	139-155
Number of pages	17
ISBN (Print)	9783030585884
DOIs	https://doi.org/10.1007/978-3-030-58589-1_9
State	Published - Nov 12 2020
Externally published	Yes

Bibliographical note

KAUST Repository Item: Exported on 2022-07-01
Acknowledgements: D.L. was supported by a Stanford Graduate Fellowship. C.M. was supported by an ORISE Intelligence Community Postdoctoral Fellowship. G.W. was supported by an NSF CAREER Award (IIS 1553333), a Sloan Fellowship, by the KAUST Office of Sponsored Research through the Visual Computing Center CCF grant, and a PECASE by the ARL.
This publication acknowledges KAUST support, but has no KAUST affiliated authors.

Access to Document

10.1007/978-3-030-58589-1_9

Cite this

@inproceedings{14acbe6db60d4182a207040cea2a5d15,

title = "Disambiguating Monocular Depth Estimation with a Single Transient",

abstract = "Monocular depth estimation algorithms successfully predict the relative depth order of objects in a scene. However, because of the fundamental scale ambiguity associated with monocular images, these algorithms fail at correctly predicting true metric depth. In this work, we demonstrate how a depth histogram of the scene, which can be readily captured using a single-pixel time-resolved detector, can be fused with the output of existing monocular depth estimation algorithms to resolve the depth ambiguity problem. We validate this novel sensor fusion technique experimentally and in extensive simulation. We show that it significantly improves the performance of several state-of-the-art monocular depth estimation algorithms.",

author = "Mark Nishimura and Lindell, {David B.} and Metzler, {Christopher A.} and Gordon Wetzstein",

note = "KAUST Repository Item: Exported on 2022-07-01 Acknowledgements: D.L. was supported by a Stanford Graduate Fellowship. C.M. was supported by an ORISE Intelligence Community Postdoctoral Fellowship. G.W. was supported by an NSF CAREER Award (IIS 1553333), a Sloan Fellowship, by the KAUST Office of Sponsored Research through the Visual Computing Center CCF grant, and a PECASE by the ARL. This publication acknowledges KAUST support, but has no KAUST affiliated authors.",

year = "2020",

month = nov,

day = "12",

doi = "10.1007/978-3-030-58589-1_9",

language = "English (US)",

isbn = "9783030585884",

pages = "139--155",

booktitle = "Computer Vision – ECCV 2020",

publisher = "Springer International Publishing",

}

TY - GEN

T1 - Disambiguating Monocular Depth Estimation with a Single Transient

AU - Nishimura, Mark

AU - Lindell, David B.

AU - Metzler, Christopher A.

AU - Wetzstein, Gordon

N1 - KAUST Repository Item: Exported on 2022-07-01 Acknowledgements: D.L. was supported by a Stanford Graduate Fellowship. C.M. was supported by an ORISE Intelligence Community Postdoctoral Fellowship. G.W. was supported by an NSF CAREER Award (IIS 1553333), a Sloan Fellowship, by the KAUST Office of Sponsored Research through the Visual Computing Center CCF grant, and a PECASE by the ARL. This publication acknowledges KAUST support, but has no KAUST affiliated authors.

PY - 2020/11/12

Y1 - 2020/11/12

N2 - Monocular depth estimation algorithms successfully predict the relative depth order of objects in a scene. However, because of the fundamental scale ambiguity associated with monocular images, these algorithms fail at correctly predicting true metric depth. In this work, we demonstrate how a depth histogram of the scene, which can be readily captured using a single-pixel time-resolved detector, can be fused with the output of existing monocular depth estimation algorithms to resolve the depth ambiguity problem. We validate this novel sensor fusion technique experimentally and in extensive simulation. We show that it significantly improves the performance of several state-of-the-art monocular depth estimation algorithms.

AB - Monocular depth estimation algorithms successfully predict the relative depth order of objects in a scene. However, because of the fundamental scale ambiguity associated with monocular images, these algorithms fail at correctly predicting true metric depth. In this work, we demonstrate how a depth histogram of the scene, which can be readily captured using a single-pixel time-resolved detector, can be fused with the output of existing monocular depth estimation algorithms to resolve the depth ambiguity problem. We validate this novel sensor fusion technique experimentally and in extensive simulation. We show that it significantly improves the performance of several state-of-the-art monocular depth estimation algorithms.

UR - http://hdl.handle.net/10754/679537

UR - https://link.springer.com/10.1007/978-3-030-58589-1_9

UR - http://www.scopus.com/inward/record.url?scp=85097375767&partnerID=8YFLogxK

U2 - 10.1007/978-3-030-58589-1_9

DO - 10.1007/978-3-030-58589-1_9

M3 - Conference contribution

SN - 9783030585884

SP - 139

EP - 155

BT - Computer Vision – ECCV 2020

PB - Springer International Publishing

ER -

Disambiguating Monocular Depth Estimation with a Single Transient

Abstract

Bibliographical note

Access to Document

Other files and links

Fingerprint

Cite this