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: Contribution to conference › Paper › peer-review

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. Code is available https://github.com/princeton-vl/DeepV2D.

Original language	English (US)
State	Published - 2020
Event	8th International Conference on Learning Representations, ICLR 2020 - Addis Ababa, Ethiopia Duration: Apr 30 2020 → …

Conference

Conference	8th International Conference on Learning Representations, ICLR 2020
Country/Territory	Ethiopia
City	Addis Ababa
Period	4/30/20 → …

All Science Journal Classification (ASJC) codes

Education
Linguistics and Language
Language and Linguistics
Computer Science Applications

Cite this

@conference{f7e29547b6a84bbdb2cbfed16ca9d94f,

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. Code is available https://github.com/princeton-vl/DeepV2D.",

author = "Zachary Teed and Jia Deng",

note = "Publisher Copyright: {\textcopyright} 2020 8th International Conference on Learning Representations, ICLR 2020. All rights reserved.; 8th International Conference on Learning Representations, ICLR 2020 ; Conference date: 30-04-2020",

year = "2020",

language = "English (US)",

}

TY - CONF

T1 - DEEPV2D

T2 - 8th International Conference on Learning Representations, ICLR 2020

AU - Teed, Zachary

AU - Deng, Jia

PY - 2020

Y1 - 2020

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. Code is available https://github.com/princeton-vl/DeepV2D.

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. Code is available https://github.com/princeton-vl/DeepV2D.

UR - https://www.scopus.com/pages/publications/85145825947

UR - https://www.scopus.com/pages/publications/85145825947#tab=citedBy

M3 - Paper

AN - SCOPUS:85145825947

Y2 - 30 April 2020

ER -

DEEPV2D: VIDEO TO DEPTH WITH DIFFERENTIABLE STRUCTURE FROM MOTION

Abstract

Conference

All Science Journal Classification (ASJC) codes

Other files and links

Fingerprint

Cite this