Self-supervised paradigms for monocular depth estimation are very appealing since they do not require ground truth annotations at all. Despite the astonishing results yielded by such methodologies, learning to reason about the uncertainty of the estimated depth maps is of paramount importance for practical applications, yet uncharted in the literature. Purposely, we explore for the first time how to estimate the uncertainty for this task and how this affects depth accuracy, proposing a novel peculiar technique specifically designed for self-supervised approaches. On the standard KITTI dataset, we exhaustively assess the performance of each method with different self-supervised paradigms. Such evaluation highlights that our proposal i) always improves depth accuracy significantly and ii) yields state-of-the-art results concerning uncertainty estimation when training on sequences and competitive results uniquely deploying stereo pairs.

M. Poggi, F.A. (2020). On the Uncertainty of Self-Supervised Monocular Depth Estimation. IEEE/CVF [10.1109/CVPR42600.2020.00329].

On the Uncertainty of Self-Supervised Monocular Depth Estimation

M. Poggi;F. Aleotti;F. Tosi;S. Mattoccia
2020

Abstract

Self-supervised paradigms for monocular depth estimation are very appealing since they do not require ground truth annotations at all. Despite the astonishing results yielded by such methodologies, learning to reason about the uncertainty of the estimated depth maps is of paramount importance for practical applications, yet uncharted in the literature. Purposely, we explore for the first time how to estimate the uncertainty for this task and how this affects depth accuracy, proposing a novel peculiar technique specifically designed for self-supervised approaches. On the standard KITTI dataset, we exhaustively assess the performance of each method with different self-supervised paradigms. Such evaluation highlights that our proposal i) always improves depth accuracy significantly and ii) yields state-of-the-art results concerning uncertainty estimation when training on sequences and competitive results uniquely deploying stereo pairs.
2020
2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
3224
3234
M. Poggi, F.A. (2020). On the Uncertainty of Self-Supervised Monocular Depth Estimation. IEEE/CVF [10.1109/CVPR42600.2020.00329].
M. Poggi, F. Aleotti, F. Tosi, S. Mattoccia
File in questo prodotto:
File Dimensione Formato  
Poggi_On_the_Uncertainty_CVPR_2020_supplemental.pdf

accesso aperto

Descrizione: Supplementary material
Tipo: File Supplementare
Licenza: Licenza per accesso libero gratuito
Dimensione 8.48 MB
Formato Adobe PDF
8.48 MB Adobe PDF Visualizza/Apri
Poggi_On_the_Uncertainty_of_Self-Supervised_Monocular_Depth_Estimation_CVPR_2020_paper.pdf

accesso aperto

Tipo: Postprint
Licenza: Licenza per accesso libero gratuito
Dimensione 932.62 kB
Formato Adobe PDF
932.62 kB Adobe PDF Visualizza/Apri

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11585/764263
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 177
  • ???jsp.display-item.citation.isi??? 133
social impact