Guiding Monocular Depth Estimation Using Depth-Attention Volume

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F20%3A00346894" target="_blank" >RIV/68407700:21230/20:00346894 - isvavai.cz</a>

Výsledek na webu

<a href="https://doi.org/10.1007/978-3-030-58574-7_35" target="_blank" >https://doi.org/10.1007/978-3-030-58574-7_35</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1007/978-3-030-58574-7_35" target="_blank" >10.1007/978-3-030-58574-7_35</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Guiding Monocular Depth Estimation Using Depth-Attention Volume

Popis výsledku v původním jazyce

Recovering the scene depth from a single image is an ill-posed problem that requires additional priors, often referred to as monocular depth cues, to disambiguate different 3D interpretations. In recent works, those priors have been learned in an end-to-end manner from large datasets by using deep neural networks. In this paper, we propose guiding depth estimation to favor planar structures that are ubiquitous especially in indoor environments. This is achieved by incorporating a non-local coplanarity constraint to the network with a novel attention mechanism called depth-attention volume (DAV). Experiments on two popular indoor datasets, namely NYU-Depth-v2 and ScanNet, show that our method achieves state-of-the-art depth estimation results while using only a fraction of the number of parameters needed by the competing methods. Code is available at: https://github.com/HuynhLam/DAV.

Název v anglickém jazyce

Guiding Monocular Depth Estimation Using Depth-Attention Volume

Popis výsledku anglicky

Recovering the scene depth from a single image is an ill-posed problem that requires additional priors, often referred to as monocular depth cues, to disambiguate different 3D interpretations. In recent works, those priors have been learned in an end-to-end manner from large datasets by using deep neural networks. In this paper, we propose guiding depth estimation to favor planar structures that are ubiquitous especially in indoor environments. This is achieved by incorporating a non-local coplanarity constraint to the network with a novel attention mechanism called depth-attention volume (DAV). Experiments on two popular indoor datasets, namely NYU-Depth-v2 and ScanNet, show that our method achieves state-of-the-art depth estimation results while using only a fraction of the number of parameters needed by the competing methods. Code is available at: https://github.com/HuynhLam/DAV.

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Projekt

<a href="/cs/project/EF16_019%2F0000765" target="_blank" >EF16_019/0000765: Výzkumné centrum informatiky</a><br>

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Rok uplatnění

2020

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název statě ve sborníku

Computer Vision - ECCV 2020, Part XXVI

ISBN

978-3-030-58573-0

ISSN

0302-9743

e-ISSN

1611-3349

Počet stran výsledku

17

Strana od-do

581-597

Název nakladatele

Springer

Místo vydání

Cham

Místo konání akce

Glasgow

Datum konání akce

23. 8. 2020

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

—