Monocular Depth Estimation Using Multi-Scale Continuous CRFs as Sequential Deep Networks

Monocular Depth Estimation Using Multi-Scale Continuous CRFs as Sequential Deep Networks

Depth cues have been proved very useful in various computer vision and robotic tasks. This paper addresses the problem of monocular depth estimation from a single still image. Inspired by the effectiveness of recent works on multi-scale convolutional neural networks (CNN), we propose a deep model wh...

Ausführliche Beschreibung

Bibliographische Detailangaben
Veröffentlicht in:IEEE transactions on pattern analysis and machine intelligence. - 1979. - 41(2019), 6 vom: 26. Juni, Seite 1426-1440
1. Verfasser: Xu, Dan (VerfasserIn)
Weitere Verfasser: Ricci, Elisa, Wanli Ouyang, Xiaogang Wang, Sebe, Nicu
Format: Online-Aufsatz
Sprache:English
Veröffentlicht: 2019
Zugriff auf das übergeordnete Werk:IEEE transactions on pattern analysis and machine intelligence
Schlagworte:Journal Article
LEADER 01000naa a22002652 4500
001 NLM286368439
003 DE-627
005 20231225051539.0
007 cr uuu---uuuuu
008 231225s2019 xx |||||o 00| ||eng c
024 7 |a 10.1109/TPAMI.2018.2839602  |2 doi 
028 5 2 |a pubmed24n0954.xml 
035 |a (DE-627)NLM286368439 
035 |a (NLM)29994300 
040 |a DE-627  |b ger  |c DE-627  |e rakwb 
041 |a eng 
100 1 |a Xu, Dan  |e verfasserin  |4 aut 
245 1 0 |a Monocular Depth Estimation Using Multi-Scale Continuous CRFs as Sequential Deep Networks 
264 1 |c 2019 
336 |a Text  |b txt  |2 rdacontent 
337 |a ƒaComputermedien  |b c  |2 rdamedia 
338 |a ƒa Online-Ressource  |b cr  |2 rdacarrier 
500 |a Date Revised 20.11.2019 
500 |a published: Print-Electronic 
500 |a Citation Status PubMed-not-MEDLINE 
520 |a Depth cues have been proved very useful in various computer vision and robotic tasks. This paper addresses the problem of monocular depth estimation from a single still image. Inspired by the effectiveness of recent works on multi-scale convolutional neural networks (CNN), we propose a deep model which fuses complementary information derived from multiple CNN side outputs. Different from previous methods using concatenation or weighted average schemes, the integration is obtained by means of continuous Conditional Random Fields (CRFs). In particular, we propose two different variations, one based on a cascade of multiple CRFs, the other on a unified graphical model. By designing a novel CNN implementation of mean-field updates for continuous CRFs, we show that both proposed models can be regarded as sequential deep networks and that training can be performed end-to-end. Through an extensive experimental evaluation, we demonstrate the effectiveness of the proposed approach and establish new state of the art results for the monocular depth estimation task on three publicly available datasets, i.e., NYUD-V2, Make3D and KITTI 
650 4 |a Journal Article 
700 1 |a Ricci, Elisa  |e verfasserin  |4 aut 
700 1 |a Wanli Ouyang  |e verfasserin  |4 aut 
700 1 |a Xiaogang Wang  |e verfasserin  |4 aut 
700 1 |a Sebe, Nicu  |e verfasserin  |4 aut 
773 0 8 |i Enthalten in  |t IEEE transactions on pattern analysis and machine intelligence  |d 1979  |g 41(2019), 6 vom: 26. Juni, Seite 1426-1440  |w (DE-627)NLM098212257  |x 1939-3539  |7 nnns 
773 1 8 |g volume:41  |g year:2019  |g number:6  |g day:26  |g month:06  |g pages:1426-1440 
856 4 0 |u http://dx.doi.org/10.1109/TPAMI.2018.2839602  |3 Volltext 
912 |a GBV_USEFLAG_A 
912 |a SYSFLAG_A 
912 |a GBV_NLM 
912 |a GBV_ILN_350 
951 |a AR 
952 |d 41  |j 2019  |e 6  |b 26  |c 06  |h 1426-1440