Vision UFormer: Long-Range Monocular Absolute Depth Estimation

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216305%3A26230%2F23%3APU149297" target="_blank" >RIV/00216305:26230/23:PU149297 - isvavai.cz</a>

Výsledek na webu

<a href="https://www.sciencedirect.com/science/article/pii/S0097849323000262" target="_blank" >https://www.sciencedirect.com/science/article/pii/S0097849323000262</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1016/j.cag.2023.02.003" target="_blank" >10.1016/j.cag.2023.02.003</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Vision UFormer: Long-Range Monocular Absolute Depth Estimation

Popis výsledku v původním jazyce

We introduce Vision UFormer (ViUT), a novel deep neural long-range monocular depth estimator. The input is an RGB image, and the output is an image that stores the absolute distance of the object in the scene as its per-pixel values. ViUT consists of a Transformer encoder and a ResNet decoder combined with UNet style of skip connections. It is trained on 1M images across ten datasets in a staged regime that starts with easier-to-predict data such as indoor photographs and continues to more complex long-range outdoor scenes. We show that ViUT provides comparable results for normalized relative distances and short-range classical datasets such as NYUv2 and KITTI. We further show that it successfully estimates of absolute long-range depth in meters. We validate ViUT on a wide variety of long-range scenes showing its high estimation capabilities with a relative improvement of up to 23%. Absolute depth estimation finds application in many areas, and we show its usability in image composition, range annotation, defocus, and scene reconstruction.

Název v anglickém jazyce

Vision UFormer: Long-Range Monocular Absolute Depth Estimation

Popis výsledku anglicky

We introduce Vision UFormer (ViUT), a novel deep neural long-range monocular depth estimator. The input is an RGB image, and the output is an image that stores the absolute distance of the object in the scene as its per-pixel values. ViUT consists of a Transformer encoder and a ResNet decoder combined with UNet style of skip connections. It is trained on 1M images across ten datasets in a staged regime that starts with easier-to-predict data such as indoor photographs and continues to more complex long-range outdoor scenes. We show that ViUT provides comparable results for normalized relative distances and short-range classical datasets such as NYUv2 and KITTI. We further show that it successfully estimates of absolute long-range depth in meters. We validate ViUT on a wide variety of long-range scenes showing its high estimation capabilities with a relative improvement of up to 23%. Absolute depth estimation finds application in many areas, and we show its usability in image composition, range annotation, defocus, and scene reconstruction.

Druh

J_imp - Článek v periodiku v databázi Web of Science

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/LTAIZ19004" target="_blank" >LTAIZ19004: Topografická analýza obrazu s využitím metod hlubokého učení</a><br>

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)<br>S - Specificky vyzkum na vysokych skolach

Rok uplatnění

2023

Kód důvěrnosti údajů

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

Název periodika

COMPUTERS & GRAPHICS-UK

ISSN

0097-8493

e-ISSN

1873-7684

Svazek periodika

111

Číslo periodika v rámci svazku

4

Stát vydavatele periodika

GB - Spojené království Velké Británie a Severního Irska

Počet stran výsledku

10

Strana od-do

180-189

Kód UT WoS článku

000954860700001

EID výsledku v databázi Scopus

2-s2.0-85149382691