2022
DOI: 10.1016/j.dsp.2022.103441
|View full text |Cite
|
Sign up to set email alerts
|

Single image depth estimation: An overview

Help me understand this report
View preprint versions

Search citation statements

Order By: Relevance

Paper Sections

Select...
5

Citation Types

0
23
0

Year Published

2022
2022
2024
2024

Publication Types

Select...
5
3
2

Relationship

0
10

Authors

Journals

citations
Cited by 53 publications
(23 citation statements)
references
References 66 publications
0
23
0
Order By: Relevance
“…However, carrying out ground surveys is impractical since spots of interest could be hard or even dangerous to access and field studies would drastically reduce the automation potential of river camera images. A third solution that would consist in merging the camera images with digital elevation models can only be performed manually at this stage, as current literature suggests that deep learning methods are not accurate enough to perform such tasks (Mertan et al, 2021). An object detection approach has also been considered to evaluate flood situations in urban areas (Rizk et al, 2022).…”
Section: Introductionmentioning
confidence: 99%
“…However, carrying out ground surveys is impractical since spots of interest could be hard or even dangerous to access and field studies would drastically reduce the automation potential of river camera images. A third solution that would consist in merging the camera images with digital elevation models can only be performed manually at this stage, as current literature suggests that deep learning methods are not accurate enough to perform such tasks (Mertan et al, 2021). An object detection approach has also been considered to evaluate flood situations in urban areas (Rizk et al, 2022).…”
Section: Introductionmentioning
confidence: 99%
“…Current data-driven methods predict depth by learning implicit structural and semantic information that provides enough monocular cues for depth estimation. This requires the network to look at bigger parts of the scene [2], which has been addressed by many works [3], [4] in the field of single-view depth estimation in recent years.…”
Section: Introductionmentioning
confidence: 99%
“…D EPTH estimation is a crucial challenge that is used in a variety of computer vision applications, including 3D vision [1], 3D face recognition [2], and autonomous vehicles [3] due to the low cost of consumer depth cameras and real-time performances. Raw depth maps, on the other hand, continue to face significant acquisition distortion and detailed corruption.…”
Section: Introductionmentioning
confidence: 99%