On Monocular Depth Estimation and Uncertainty Quantification using Classification Approaches for Regression - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2022

On Monocular Depth Estimation and Uncertainty Quantification using Classification Approaches for Regression

Résumé

Monocular depth is important in many tasks, such as 3D reconstruction and autonomous driving. Deep learning based models achieve state-of-the-art performance in this field. A set of novel approaches for estimating monocular depth consists of transforming the regression task into a classification one. However, there is a lack of detailed descriptions and comparisons for Classification Approaches for Regression (CAR) in the community and no in-depth exploration of their potential for uncertainty estimation. To this end, this paper will introduce a taxonomy and summary of CAR approaches, a new uncertainty estimation solution for CAR, and a set of experiments on depth accuracy and uncertainty quantification for CAR-based models on KITTI dataset. The experiments reflect the differences in the portability of various CAR methods on two backbones. Meanwhile, the newly proposed method for uncertainty estimation can outperform the ensembling method with only one forward propagation.
Fichier principal
Vignette du fichier
2202.12369.pdf (2.95 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03775941 , version 1 (18-10-2022)

Identifiants

Citer

Xuanlong Yu, Gianni Franchi, Emanuel Aldea. On Monocular Depth Estimation and Uncertainty Quantification using Classification Approaches for Regression. 29th IEEE International Conference on Image Processing (IEEE ICIP), Oct 2022, Bordeaux, France. ⟨10.1109/ICIP46576.2022.9897930⟩. ⟨hal-03775941⟩
55 Consultations
25 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More