DEEP MULTI-SCALE ARCHITECTURES FOR MONOCULAR DEPTH ESTIMATION

Michel Moukari 1, 2 Sylvaine Picard 2 Loic Simon 1 Frédéric Jurie 1
1 Equipe Image - Laboratoire GREYC - UMR6072
GREYC - Groupe de Recherche en Informatique, Image, Automatique et Instrumentation de Caen
Abstract : 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.
Document type :
Conference papers
Liste complète des métadonnées

Cited literature [10 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-01803817
Contributor : Frederic Jurie <>
Submitted on : Thursday, May 31, 2018 - 6:41:09 AM
Last modification on : Thursday, February 7, 2019 - 2:46:42 PM
Document(s) archivé(s) le : Saturday, September 1, 2018 - 12:39:31 PM

Identifiers

  • HAL Id : hal-01803817, version 1
  • ARXIV : 1806.03051

Citation

Michel Moukari, Sylvaine Picard, Loic Simon, Frédéric Jurie. DEEP MULTI-SCALE ARCHITECTURES FOR MONOCULAR DEPTH ESTIMATION. IEEE International Conference on Image Processing, Oct 2018, Athens, Greece. ⟨hal-01803817⟩

Share

Metrics

Record views

127

Files downloads

171