Boosting Monocular Depth Estimation with Lightweight 3D Point Fusion

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F21%3A00354697" target="_blank" >RIV/68407700:21230/21:00354697 - isvavai.cz</a>

Výsledek na webu

<a href="https://doi.org/10.1109/ICCV48922.2021.01253" target="_blank" >https://doi.org/10.1109/ICCV48922.2021.01253</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1109/ICCV48922.2021.01253" target="_blank" >10.1109/ICCV48922.2021.01253</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Boosting Monocular Depth Estimation with Lightweight 3D Point Fusion

Popis výsledku v původním jazyce

In this paper, we propose enhancing monocular depthestimation by adding 3D points as depth guidance. Un-like existing depth completion methods, our approach per-forms well on extremely sparse and unevenly distributedpoint clouds, which makes it agnostic to the source of the3D points. We achieve this by introducing a novel multi-scale 3D point fusion network that is both lightweight andefficient. We demonstrate its versatility on two differentdepth estimation problems where the 3D points have beenacquired with conventional structure-from-motion and Li-DAR. In both cases, our network performs on par with state-of-the-art depth completion methods and achieves signifi-cantly higher accuracy when only a small number of pointsis used while being more compact in terms of the num-ber of parameters. We show that our method outperformssome contemporary deep learning based multi-view stereoand structure-from-motion methods both in accuracy and incompactness.

Název v anglickém jazyce

Boosting Monocular Depth Estimation with Lightweight 3D Point Fusion

Popis výsledku anglicky

In this paper, we propose enhancing monocular depthestimation by adding 3D points as depth guidance. Un-like existing depth completion methods, our approach per-forms well on extremely sparse and unevenly distributedpoint clouds, which makes it agnostic to the source of the3D points. We achieve this by introducing a novel multi-scale 3D point fusion network that is both lightweight andefficient. We demonstrate its versatility on two differentdepth estimation problems where the 3D points have beenacquired with conventional structure-from-motion and Li-DAR. In both cases, our network performs on par with state-of-the-art depth completion methods and achieves signifi-cantly higher accuracy when only a small number of pointsis used while being more compact in terms of the num-ber of parameters. We show that our method outperformssome contemporary deep learning based multi-view stereoand structure-from-motion methods both in accuracy and incompactness.

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

2021

Kód důvěrnosti údajů

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

Název statě ve sborníku

ICCV2021: Proceedings of the International Conference on Computer Vision

ISBN

978-1-6654-2812-5

ISSN

1550-5499

e-ISSN

2380-7504

Počet stran výsledku

10

Strana od-do

12767-12776

Název nakladatele

IEEE

Místo vydání

Piscataway

Místo konání akce

Montreal

Datum konání akce

11. 10. 2021

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

—