DEEP MULTI-SCALE ARCHITECTURES FOR MONOCULAR DEPTH ESTIMATION - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2018

DEEP MULTI-SCALE ARCHITECTURES FOR MONOCULAR DEPTH ESTIMATION

Sylvaine Picard
  • Fonction : Auteur
  • PersonId : 1032554
Loïc Simon

Résumé

This paper aims at understanding the role of multi-scale information in the estimation of depth from monocular images. More precisely, the paper investigates four different deep CNN architectures, designed to explicitly make use of multi-scale features along the network, and compare them to a state-of-the-art single-scale approach. The paper also shows that involving multi-scale features in depth estimation not only improves the performance in terms of accuracy, but also gives qualitatively better depth maps. Experiments are done on the widely used NYU Depth dataset, on which the proposed method achieves state-of-the-art performance.
Fichier principal
Vignette du fichier
submission_main.pdf (1.37 Mo) Télécharger le fichier
results.key (1.8 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-01803817 , version 1 (31-05-2018)

Identifiants

Citer

Michel Moukari, Sylvaine Picard, Loïc Simon, Frédéric Jurie. DEEP MULTI-SCALE ARCHITECTURES FOR MONOCULAR DEPTH ESTIMATION. 2018 25th IEEE International Conference on Image Processing (ICIP, Oct 2018, Athens, Greece. ⟨10.1109/ICIP.2018.8451408⟩. ⟨hal-01803817⟩
282 Consultations
279 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More