DEEPV2D: VIDEO TO DEPTH WITH DIFFERENTIABLE STRUCTURE FROM MOTION

Zachary Teed; Jia Deng

DEEPV2D: VIDEO TO DEPTH WITH DIFFERENTIABLE STRUCTURE FROM MOTION

Zachary Teed, Jia Deng

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

Abstract

We propose DeepV2D, an end-to-end deep learning architecture for predicting depth from video. DeepV2D combines the representation ability of neural networks with the geometric principles governing image formation. We compose a collection of classical geometric algorithms, which are converted into trainable modules and combined into an end-to-end differentiable architecture. DeepV2D interleaves two stages: motion estimation and depth estimation. During inference, motion and depth estimation are alternated and converge to accurate depth.

Original language	English (US)
Title of host publication	8th International Conference on Learning Representations, ICLR 2020
Publisher	International Conference on Learning Representations, ICLR
State	Published - Jan 1 2020
Externally published	Yes

Cite this

@inproceedings{ae348412320e41b4b8d32085ca8ff033,

title = "DEEPV2D: VIDEO TO DEPTH WITH DIFFERENTIABLE STRUCTURE FROM MOTION",

abstract = "We propose DeepV2D, an end-to-end deep learning architecture for predicting depth from video. DeepV2D combines the representation ability of neural networks with the geometric principles governing image formation. We compose a collection of classical geometric algorithms, which are converted into trainable modules and combined into an end-to-end differentiable architecture. DeepV2D interleaves two stages: motion estimation and depth estimation. During inference, motion and depth estimation are alternated and converge to accurate depth.",

author = "Zachary Teed and Jia Deng",

note = "KAUST Repository Item: Exported on 2023-04-05 Acknowledged KAUST grant number(s): OSR-2015-CRG4-2639 Acknowledgements: We would like to thank Zhaoheng Zheng for helping with baseline experiments. This work was partially funded by the Toyota Research Institute, the King Abdullah University of Science and Technology (KAUST) Office of Sponsored Research (OSR) under Award No. OSR-2015-CRG4-2639, and the National Science Foundation under Grant No. 1617767. This publication acknowledges KAUST support, but has no KAUST affiliated authors.",

year = "2020",

month = jan,

day = "1",

language = "English (US)",

booktitle = "8th International Conference on Learning Representations, ICLR 2020",

publisher = "International Conference on Learning Representations, ICLR",

}

TY - GEN

T1 - DEEPV2D: VIDEO TO DEPTH WITH DIFFERENTIABLE STRUCTURE FROM MOTION

AU - Teed, Zachary

AU - Deng, Jia

N1 - KAUST Repository Item: Exported on 2023-04-05 Acknowledged KAUST grant number(s): OSR-2015-CRG4-2639 Acknowledgements: We would like to thank Zhaoheng Zheng for helping with baseline experiments. This work was partially funded by the Toyota Research Institute, the King Abdullah University of Science and Technology (KAUST) Office of Sponsored Research (OSR) under Award No. OSR-2015-CRG4-2639, and the National Science Foundation under Grant No. 1617767. This publication acknowledges KAUST support, but has no KAUST affiliated authors.

PY - 2020/1/1

Y1 - 2020/1/1

N2 - We propose DeepV2D, an end-to-end deep learning architecture for predicting depth from video. DeepV2D combines the representation ability of neural networks with the geometric principles governing image formation. We compose a collection of classical geometric algorithms, which are converted into trainable modules and combined into an end-to-end differentiable architecture. DeepV2D interleaves two stages: motion estimation and depth estimation. During inference, motion and depth estimation are alternated and converge to accurate depth.

AB - We propose DeepV2D, an end-to-end deep learning architecture for predicting depth from video. DeepV2D combines the representation ability of neural networks with the geometric principles governing image formation. We compose a collection of classical geometric algorithms, which are converted into trainable modules and combined into an end-to-end differentiable architecture. DeepV2D interleaves two stages: motion estimation and depth estimation. During inference, motion and depth estimation are alternated and converge to accurate depth.

UR - http://hdl.handle.net/10754/690868

UR - https://openreview.net/forum?id=HJeO7RNKPr

UR - http://www.scopus.com/inward/record.url?scp=85145825947&partnerID=8YFLogxK

M3 - Conference contribution

BT - 8th International Conference on Learning Representations, ICLR 2020

PB - International Conference on Learning Representations, ICLR

ER -

DEEPV2D: VIDEO TO DEPTH WITH DIFFERENTIABLE STRUCTURE FROM MOTION

Abstract

Other files and links

Fingerprint

Cite this