Title
Single-View and Multiview Depth Fusion.
Abstract
Dense and accurate 3-D mapping from a monocular sequence is a key technology for several applications and still an open research area. This letter leverages recent results on single-view convolutional network (CNN)-based depth estimation and fuses them with multiview depth estimation. Both approaches present complementary strengths. Multiview depth is highly accurate but only in high-texture areas...
Year
DOI
Venue
2017
10.1109/LRA.2017.2715400
IEEE Robotics and Automation Letters
Keywords
Field
DocType
Estimation,Image reconstruction,Fuses,Proposals,Training,Three-dimensional displays,Periodic structures
Open research,Pattern recognition,Computer science,Fusion,Image content,Local structure,Coherence (physics),Artificial intelligence,Fuse (electrical),Monocular
Journal
Volume
Issue
ISSN
2
4
2377-3766
Citations 
PageRank 
References 
3
0.38
24
Authors
4
Name
Order
Citations
PageRank
José M. Fácil1291.90
Alejo Concha2373.46
L. Montesano365342.58
Javier Civera475648.61