A New Distributional Ranking Loss with Uncertainty: Illustrated in Relative Depth Estimation

Alican Mertan, Yusuf Huseyin Sahin, Damien Jade Duff, Gozde Unal

Araştırma sonucu: Kitap/Rapor/Konferans Bildirisinde BölümKonferans katkısıbilirkişi

8 Atıf (Scopus)

Özet

We propose a new approach for the problem of relative depth estimation from a single image. Instead of directly regressing over depth scores, we formulate the problem as estimation of a probability distribution over depth and aim to learn the parameters of the distributions which maximize the likelihood of the given data. To train our model, we propose a new ranking loss, Distributional Loss, which tries to increase the probability of farther pixel's depth being greater than the closer pixel's depth. Our proposed approach allows our model to output confidence in its estimation in the form of standard deviation of the distribution. We achieve state of the art results against a number of baselines while providing confidence in our estimations. Our analysis show that estimated confidence is actually a good indicator of accuracy. We investigate the usage of confidence information in a downstream task of metric depth estimation, to increase its performance.

Orijinal dilİngilizce
Ana bilgisayar yayını başlığıProceedings - 2020 International Conference on 3D Vision, 3DV 2020
YayınlayanInstitute of Electrical and Electronics Engineers Inc.
Sayfalar1079-1088
Sayfa sayısı10
ISBN (Elektronik)9781728181288
DOI'lar
Yayın durumuYayınlandı - Kas 2020
Etkinlik8th International Conference on 3D Vision, 3DV 2020 - Virtual, Fukuoka, Japan
Süre: 25 Kas 202028 Kas 2020

Yayın serisi

AdıProceedings - 2020 International Conference on 3D Vision, 3DV 2020

???event.eventtypes.event.conference???

???event.eventtypes.event.conference???8th International Conference on 3D Vision, 3DV 2020
Ülke/BölgeJapan
ŞehirVirtual, Fukuoka
Periyot25/11/2028/11/20

Bibliyografik not

Publisher Copyright:
© 2020 IEEE.

Parmak izi

A New Distributional Ranking Loss with Uncertainty: Illustrated in Relative Depth Estimation' araştırma başlıklarına git. Birlikte benzersiz bir parmak izi oluştururlar.

Alıntı Yap