Lap-Based Video Frame Interpolation

Tejas Jayashankar; Pierre Moulin; Thierry Blu; Chris Gilliam

doi:10.1109/ICIP.2019.8803484

Lap-Based Video Frame Interpolation

Tejas Jayashankar
, Pierre Moulin
, Thierry Blu
, Chris Gilliam

Electronic, Electrical and Systems Engineering

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

3 Citations (Scopus)

Abstract

High-quality video frame interpolation often necessitates accurate motion estimation, which can be obtained using modern optical flow methods. In this paper, we use the recently proposed Local All-Pass (LAP) algorithm to compute the optical flow between two consecutive frames. The resulting flow field is used to perform interpolation using cubic splines. We compare the interpolation results against a well-known optical flow estimation algorithm as well as against a recent con-volutional neural network scheme for video frame interpolation. Qualitative and quantitative results show that the LAP algorithm performs fast, high-quality video frame interpolation, and perceptually outperforms the neural network and the Lucas-Kanade method on a variety of test sequences.

Original language	English
Title of host publication	2019 IEEE International Conference on Image Processing, ICIP 2019 - Proceedings
Publisher	IEEE Computer Society Press
Pages	4195-4199
Number of pages	5
ISBN (Electronic)	9781538662496
DOIs	https://doi.org/10.1109/ICIP.2019.8803484
Publication status	Published - Sept 2019
Event	26th IEEE International Conference on Image Processing, ICIP 2019 - Taipei, Taiwan, Province of China Duration: 22 Sept 2019 → 25 Sept 2019

Publication series

Name	Proceedings - International Conference on Image Processing, ICIP
Volume	2019-September
ISSN (Print)	1522-4880

Conference

Conference	26th IEEE International Conference on Image Processing, ICIP 2019
Country/Territory	Taiwan, Province of China
City	Taipei
Period	22/09/19 → 25/09/19

Bibliographical note

Publisher Copyright:
© 2019 IEEE.

Keywords

Convolutional neural network
Lucas-Kanade algorithm
Optical flow
Splines
Video interpolation

ASJC Scopus subject areas

Software
Computer Vision and Pattern Recognition
Signal Processing

Access to Document

10.1109/ICIP.2019.8803484

Cite this

Jayashankar, T., Moulin, P., Blu, T., & Gilliam, C. (2019). Lap-Based Video Frame Interpolation. In 2019 IEEE International Conference on Image Processing, ICIP 2019 - Proceedings (pp. 4195-4199). Article 8803484 (Proceedings - International Conference on Image Processing, ICIP; Vol. 2019-September). IEEE Computer Society Press. https://doi.org/10.1109/ICIP.2019.8803484

@inproceedings{77bd8dc08b70473b8c43b0c929128ff9,

title = "Lap-Based Video Frame Interpolation",

abstract = "High-quality video frame interpolation often necessitates accurate motion estimation, which can be obtained using modern optical flow methods. In this paper, we use the recently proposed Local All-Pass (LAP) algorithm to compute the optical flow between two consecutive frames. The resulting flow field is used to perform interpolation using cubic splines. We compare the interpolation results against a well-known optical flow estimation algorithm as well as against a recent con-volutional neural network scheme for video frame interpolation. Qualitative and quantitative results show that the LAP algorithm performs fast, high-quality video frame interpolation, and perceptually outperforms the neural network and the Lucas-Kanade method on a variety of test sequences.",

keywords = "Convolutional neural network, Lucas-Kanade algorithm, Optical flow, Splines, Video interpolation",

author = "Tejas Jayashankar and Pierre Moulin and Thierry Blu and Chris Gilliam",

note = "Publisher Copyright: {\textcopyright} 2019 IEEE.; 26th IEEE International Conference on Image Processing, ICIP 2019 ; Conference date: 22-09-2019 Through 25-09-2019",

year = "2019",

month = sep,

doi = "10.1109/ICIP.2019.8803484",

language = "English",

series = "Proceedings - International Conference on Image Processing, ICIP",

publisher = "IEEE Computer Society Press",

pages = "4195--4199",

booktitle = "2019 IEEE International Conference on Image Processing, ICIP 2019 - Proceedings",

}

Jayashankar, T, Moulin, P, Blu, T & Gilliam, C 2019, Lap-Based Video Frame Interpolation. in 2019 IEEE International Conference on Image Processing, ICIP 2019 - Proceedings., 8803484, Proceedings - International Conference on Image Processing, ICIP, vol. 2019-September, IEEE Computer Society Press, pp. 4195-4199, 26th IEEE International Conference on Image Processing, ICIP 2019, Taipei, Taiwan, Province of China, 22/09/19. https://doi.org/10.1109/ICIP.2019.8803484

Lap-Based Video Frame Interpolation. / Jayashankar, Tejas; Moulin, Pierre; Blu, Thierry et al.
2019 IEEE International Conference on Image Processing, ICIP 2019 - Proceedings. IEEE Computer Society Press, 2019. p. 4195-4199 8803484 (Proceedings - International Conference on Image Processing, ICIP; Vol. 2019-September).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

TY - GEN

T1 - Lap-Based Video Frame Interpolation

AU - Jayashankar, Tejas

AU - Moulin, Pierre

AU - Blu, Thierry

AU - Gilliam, Chris

PY - 2019/9

Y1 - 2019/9

N2 - High-quality video frame interpolation often necessitates accurate motion estimation, which can be obtained using modern optical flow methods. In this paper, we use the recently proposed Local All-Pass (LAP) algorithm to compute the optical flow between two consecutive frames. The resulting flow field is used to perform interpolation using cubic splines. We compare the interpolation results against a well-known optical flow estimation algorithm as well as against a recent con-volutional neural network scheme for video frame interpolation. Qualitative and quantitative results show that the LAP algorithm performs fast, high-quality video frame interpolation, and perceptually outperforms the neural network and the Lucas-Kanade method on a variety of test sequences.

AB - High-quality video frame interpolation often necessitates accurate motion estimation, which can be obtained using modern optical flow methods. In this paper, we use the recently proposed Local All-Pass (LAP) algorithm to compute the optical flow between two consecutive frames. The resulting flow field is used to perform interpolation using cubic splines. We compare the interpolation results against a well-known optical flow estimation algorithm as well as against a recent con-volutional neural network scheme for video frame interpolation. Qualitative and quantitative results show that the LAP algorithm performs fast, high-quality video frame interpolation, and perceptually outperforms the neural network and the Lucas-Kanade method on a variety of test sequences.

KW - Convolutional neural network

KW - Lucas-Kanade algorithm

KW - Optical flow

KW - Splines

KW - Video interpolation

UR - https://www.scopus.com/pages/publications/85076801379

U2 - 10.1109/ICIP.2019.8803484

DO - 10.1109/ICIP.2019.8803484

M3 - Conference contribution

AN - SCOPUS:85076801379

T3 - Proceedings - International Conference on Image Processing, ICIP

SP - 4195

EP - 4199

BT - 2019 IEEE International Conference on Image Processing, ICIP 2019 - Proceedings

PB - IEEE Computer Society Press

T2 - 26th IEEE International Conference on Image Processing, ICIP 2019

Y2 - 22 September 2019 through 25 September 2019

ER -

Lap-Based Video Frame Interpolation

Abstract

Publication series

Conference

Bibliographical note

Keywords

ASJC Scopus subject areas

Access to Document

Fingerprint

Cite this