Recent works have shown the benefit of integrating Conditional Random Fields (CRFs) models into deep architectures for improving pixel-level prediction tasks. Following this line of research, in this paper we introduce a novel approach for monocular depth estimation. Similarly to previous works, our method employs a continuous CRF to fuse multi-scale information derived from different layers of a front-end Convolutional Neural Network (CNN). Differently from past works, our approach benefits from a structured attention model which automatically regulates the amount of information transferred between corresponding features at different scales. Importantly, the proposed attention model is seamlessly integrated into the CRF, allowing end-to-end training of the entire architecture. Our extensive experimental evaluation demonstrates the effectiveness of the proposed method which is competitive with previous methods on the KITTI benchmark and outperforms the state of the art on the NYU Depth V2 dataset.

Structured Attention Guided Convolutional Neural Fields for Monocular Depth Estimation / Xu, Dan; Wang, Wei; Tang, Hao; Liu, Hong; Sebe, Nicu; Ricci, Elisa. - (2018), pp. 3917-3925. (Intervento presentato al convegno CVPR tenutosi a Salt Lake City, UT, USA nel 18-23 June 2018) [10.1109/CVPR.2018.00412].

Structured Attention Guided Convolutional Neural Fields for Monocular Depth Estimation

Xu, Dan;Wang, Wei;Tang, Hao;Sebe, Nicu;Ricci, Elisa
2018-01-01

Abstract

Recent works have shown the benefit of integrating Conditional Random Fields (CRFs) models into deep architectures for improving pixel-level prediction tasks. Following this line of research, in this paper we introduce a novel approach for monocular depth estimation. Similarly to previous works, our method employs a continuous CRF to fuse multi-scale information derived from different layers of a front-end Convolutional Neural Network (CNN). Differently from past works, our approach benefits from a structured attention model which automatically regulates the amount of information transferred between corresponding features at different scales. Importantly, the proposed attention model is seamlessly integrated into the CRF, allowing end-to-end training of the entire architecture. Our extensive experimental evaluation demonstrates the effectiveness of the proposed method which is competitive with previous methods on the KITTI benchmark and outperforms the state of the art on the NYU Depth V2 dataset.
2018
IEEE/CVF Conference on Computer Vision and Pattern Recognition
Piscataway, NJ USA
IEEE
978-1-5386-6420-9
Xu, Dan; Wang, Wei; Tang, Hao; Liu, Hong; Sebe, Nicu; Ricci, Elisa
Structured Attention Guided Convolutional Neural Fields for Monocular Depth Estimation / Xu, Dan; Wang, Wei; Tang, Hao; Liu, Hong; Sebe, Nicu; Ricci, Elisa. - (2018), pp. 3917-3925. (Intervento presentato al convegno CVPR tenutosi a Salt Lake City, UT, USA nel 18-23 June 2018) [10.1109/CVPR.2018.00412].
File in questo prodotto:
File Dimensione Formato  
structured.pdf

Solo gestori archivio

Tipologia: Versione editoriale (Publisher’s layout)
Licenza: Tutti i diritti riservati (All rights reserved)
Dimensione 2.22 MB
Formato Adobe PDF
2.22 MB 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/11572/225602
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 253
  • ???jsp.display-item.citation.isi??? 216
social impact