2019
DOI: 10.1109/tip.2018.2884280
|View full text |Cite
|
Sign up to set email alerts
|

Deep Online Video Stabilization With Multi-Grid Warping Transformation Learning

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

1
96
0

Year Published

2019
2019
2023
2023

Publication Types

Select...
4
3

Relationship

0
7

Authors

Journals

citations
Cited by 109 publications
(97 citation statements)
references
References 21 publications
1
96
0
Order By: Relevance
“…With the popularity of deep learning, there are also some video stabilization methods based on deep learning. Input stabilized and jitter video to the network, and output a homography matrix to the network [ 21 ]. The objective function does not consider the effects of multi-object and parallax, so it is only effective for a single object or background shaky video.…”
Section: Related Workmentioning
confidence: 99%
“…With the popularity of deep learning, there are also some video stabilization methods based on deep learning. Input stabilized and jitter video to the network, and output a homography matrix to the network [ 21 ]. The objective function does not consider the effects of multi-object and parallax, so it is only effective for a single object or background shaky video.…”
Section: Related Workmentioning
confidence: 99%
“…One seeks to directly estimate the camera path (position), and the video stabilization can be considered as a camera path smoothing problem [36]. This formulation aims to stabilize homographic distortion cause by camera shaking, and recently a deep learning based method has been developed to learn from data registered by a mechanical stabilizer [37], which shows greater efficiency than traditional algorithms. The other type of approach models the instability of the video (or frame stream) as an appearance change [38].…”
Section: Video Stabilizationmentioning
confidence: 99%
“…More recently, convolutional neural networks have been applied to both registration [18] and stabilization [16] domains. Both methods have proposed to use a rich warping model based on Thin Plate Splines (TPS).…”
Section: Prior Workmentioning
confidence: 99%
“…1.a). Authors of StabNet [16] based their approach on a siamese convolutional network that was trained thanks to a stabilization database. This database was acquired with the help of a single handling device to which 2 different cameras were attached, only one of which was physically stabilized with a gimbal.…”
Section: Prior Workmentioning
confidence: 99%
See 1 more Smart Citation