Detail publikace

Vision UFormer: Long-Range Monocular Absolute Depth Estimation

POLÁŠEK, T. ČADÍK, M. KELLER, Y. BENEŠ, B.

Originální název

Vision UFormer: Long-Range Monocular Absolute Depth Estimation

Typ

článek v časopise ve Web of Science, Jimp

Jazyk

angličtina

Originální abstrakt

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.

Klíčová slova

Absolute Depth Estimation, Monocular Depth Prediction, Long Range Distance, Transformer, UNet, Staged Training

Autoři

POLÁŠEK, T.; ČADÍK, M.; KELLER, Y.; BENEŠ, B.

Vydáno

26. 2. 2023

Nakladatel

Elsevier

Místo

Oxford

ISSN

0097-8493

Periodikum

COMPUTERS & GRAPHICS-UK

Ročník

111

Číslo

4

Stát

Spojené království Velké Británie a Severního Irska

Strany od

180

Strany do

189

Strany počet

10

URL

https://www.sciencedirect.com/science/article/pii/S0097849323000262

BibTex

@article{BUT185048,
  author="Tomáš {Polášek} and Martin {Čadík} and Yosi {Keller} and Bedřich {Beneš}",
  title="Vision UFormer: Long-Range Monocular Absolute Depth Estimation",
  journal="COMPUTERS & GRAPHICS-UK",
  year="2023",
  volume="111",
  number="4",
  pages="180--189",
  doi="10.1016/j.cag.2023.02.003",
  issn="0097-8493",
  url="https://www.sciencedirect.com/science/article/pii/S0097849323000262"
}