AIM 2019 challenge on video temporal super-resolution: Methods and results

Seungjun Nah; Sanghyun Son; Radu Timofte; Kyoung Mu Lee; Li Siyao; Ze Pan; Xiangyu Xu; Wenxiu Sun; Myungsub Choi; Heewon Kim; Bohyung Han; Ning Xu; Bumjun Park; Songhyun Yu; Sangmin Kim; Jechang Jeong; Wang Shen; Wenbo Bao; Guangtao Zhai; Li Chen; Zhiyong Gaon; Guannan Chen; Yunhua Lu; Ran Duan; Tong Liu; Lijie Zhang; Woonsung Park; Munchurl Kim; George Pisha; Eyal Naor; Lior Aloni

doi:10.1109/ICCVW.2019.00421

AIM 2019 challenge on video temporal super-resolution: Methods and results

Seungjun Nah
, Sanghyun Son
, Radu Timofte
, Kyoung Mu Lee
, Li Siyao
, Ze Pan
, Xiangyu Xu
, Wenxiu Sun
, Myungsub Choi
, Heewon Kim
, Bohyung Han
, Ning Xu
, Bumjun Park
, Songhyun Yu
, Sangmin Kim
, Jechang Jeong
, Wang Shen
, Wenbo Bao
, Guangtao Zhai
, Li Chen

Zhiyong Gaon, Guannan Chen, Yunhua Lu, Ran Duan, Tong Liu, Lijie Zhang, Woonsung Park, Munchurl Kim, George Pisha, Eyal Naor, Lior Aloni

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

19 Scopus citations

Abstract

Videos contain various types and strengths of motions that may look unnaturally discontinuous in time when the recorded frame rate is low. This paper reviews the first AIM challenge on video temporal super-resolution (frame interpolation) with a focus on the proposed solutions and results. From low-frame-rate (15 fps) video sequences, the challenge participants are asked to submit higher-frame-rate (60 fps) video sequences by estimating temporally intermediate frames. We employ the REDS-VTSR dataset derived from diverse videos captured in a hand-held camera for training and evaluation purposes. The competition had 62 registered participants, and a total of 8 teams competed in the final testing phase. The challenge winning methods achieve the state-of-the-art in video temporal super-resolution.

Original language	English
Title of host publication	Proceedings - 2019 International Conference on Computer Vision Workshop, ICCVW 2019
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	3388-3398
Number of pages	11
ISBN (Electronic)	9781728150239
DOIs	https://doi.org/10.1109/ICCVW.2019.00421
State	Published - Oct 2019
Externally published	Yes
Event	17th IEEE/CVF International Conference on Computer Vision Workshop, ICCVW 2019 - Seoul, Korea, Republic of Duration: 27 Oct 2019 → 28 Oct 2019

Publication series

Name	Proceedings - 2019 International Conference on Computer Vision Workshop, ICCVW 2019

Conference

Conference	17th IEEE/CVF International Conference on Computer Vision Workshop, ICCVW 2019
Country/Territory	Korea, Republic of
City	Seoul
Period	27/10/19 → 28/10/19

Keywords

Frame interpolation
Video frame interpolation
Video temporal super resolution

Access to Document

10.1109/ICCVW.2019.00421

Cite this

Nah, S., Son, S., Timofte, R., Lee, K. M., Siyao, L., Pan, Z., Xu, X., Sun, W., Choi, M., Kim, H., Han, B., Xu, N., Park, B., Yu, S., Kim, S., Jeong, J., Shen, W., Bao, W., Zhai, G., ... Aloni, L. (2019). AIM 2019 challenge on video temporal super-resolution: Methods and results. In Proceedings - 2019 International Conference on Computer Vision Workshop, ICCVW 2019 (pp. 3388-3398). Article 9022180 (Proceedings - 2019 International Conference on Computer Vision Workshop, ICCVW 2019). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICCVW.2019.00421

Nah, Seungjun ; Son, Sanghyun ; Timofte, Radu et al. / AIM 2019 challenge on video temporal super-resolution : Methods and results. Proceedings - 2019 International Conference on Computer Vision Workshop, ICCVW 2019. Institute of Electrical and Electronics Engineers Inc., 2019. pp. 3388-3398 (Proceedings - 2019 International Conference on Computer Vision Workshop, ICCVW 2019).

@inproceedings{e4cb8c29232c436ca6d1f5edc5f1de74,

title = "AIM 2019 challenge on video temporal super-resolution: Methods and results",

abstract = "Videos contain various types and strengths of motions that may look unnaturally discontinuous in time when the recorded frame rate is low. This paper reviews the first AIM challenge on video temporal super-resolution (frame interpolation) with a focus on the proposed solutions and results. From low-frame-rate (15 fps) video sequences, the challenge participants are asked to submit higher-frame-rate (60 fps) video sequences by estimating temporally intermediate frames. We employ the REDS-VTSR dataset derived from diverse videos captured in a hand-held camera for training and evaluation purposes. The competition had 62 registered participants, and a total of 8 teams competed in the final testing phase. The challenge winning methods achieve the state-of-the-art in video temporal super-resolution.",

keywords = "Frame interpolation, Video frame interpolation, Video temporal super resolution",

author = "Seungjun Nah and Sanghyun Son and Radu Timofte and Lee, \{Kyoung Mu\} and Li Siyao and Ze Pan and Xiangyu Xu and Wenxiu Sun and Myungsub Choi and Heewon Kim and Bohyung Han and Ning Xu and Bumjun Park and Songhyun Yu and Sangmin Kim and Jechang Jeong and Wang Shen and Wenbo Bao and Guangtao Zhai and Li Chen and Zhiyong Gaon and Guannan Chen and Yunhua Lu and Ran Duan and Tong Liu and Lijie Zhang and Woonsung Park and Munchurl Kim and George Pisha and Eyal Naor and Lior Aloni",

note = "Publisher Copyright: {\textcopyright} 2019 IEEE.; 17th IEEE/CVF International Conference on Computer Vision Workshop, ICCVW 2019 ; Conference date: 27-10-2019 Through 28-10-2019",

year = "2019",

month = oct,

doi = "10.1109/ICCVW.2019.00421",

language = "英语",

series = "Proceedings - 2019 International Conference on Computer Vision Workshop, ICCVW 2019",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "3388--3398",

booktitle = "Proceedings - 2019 International Conference on Computer Vision Workshop, ICCVW 2019",

}

Nah, S, Son, S, Timofte, R, Lee, KM, Siyao, L, Pan, Z, Xu, X, Sun, W, Choi, M, Kim, H, Han, B, Xu, N, Park, B, Yu, S, Kim, S, Jeong, J, Shen, W, Bao, W, Zhai, G, Chen, L, Gaon, Z, Chen, G, Lu, Y, Duan, R, Liu, T, Zhang, L, Park, W, Kim, M, Pisha, G, Naor, E & Aloni, L 2019, AIM 2019 challenge on video temporal super-resolution: Methods and results. in Proceedings - 2019 International Conference on Computer Vision Workshop, ICCVW 2019., 9022180, Proceedings - 2019 International Conference on Computer Vision Workshop, ICCVW 2019, Institute of Electrical and Electronics Engineers Inc., pp. 3388-3398, 17th IEEE/CVF International Conference on Computer Vision Workshop, ICCVW 2019, Seoul, Korea, Republic of, 27/10/19. https://doi.org/10.1109/ICCVW.2019.00421

AIM 2019 challenge on video temporal super-resolution: Methods and results. / Nah, Seungjun; Son, Sanghyun; Timofte, Radu et al.
Proceedings - 2019 International Conference on Computer Vision Workshop, ICCVW 2019. Institute of Electrical and Electronics Engineers Inc., 2019. p. 3388-3398 9022180 (Proceedings - 2019 International Conference on Computer Vision Workshop, ICCVW 2019).

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

TY - GEN

T1 - AIM 2019 challenge on video temporal super-resolution

T2 - 17th IEEE/CVF International Conference on Computer Vision Workshop, ICCVW 2019

AU - Nah, Seungjun

AU - Son, Sanghyun

AU - Timofte, Radu

AU - Lee, Kyoung Mu

AU - Siyao, Li

AU - Pan, Ze

AU - Xu, Xiangyu

AU - Sun, Wenxiu

AU - Choi, Myungsub

AU - Kim, Heewon

AU - Han, Bohyung

AU - Xu, Ning

AU - Park, Bumjun

AU - Yu, Songhyun

AU - Kim, Sangmin

AU - Jeong, Jechang

AU - Shen, Wang

AU - Bao, Wenbo

AU - Zhai, Guangtao

AU - Chen, Li

AU - Gaon, Zhiyong

AU - Chen, Guannan

AU - Lu, Yunhua

AU - Duan, Ran

AU - Liu, Tong

AU - Zhang, Lijie

AU - Park, Woonsung

AU - Kim, Munchurl

AU - Pisha, George

AU - Naor, Eyal

AU - Aloni, Lior

PY - 2019/10

Y1 - 2019/10

N2 - Videos contain various types and strengths of motions that may look unnaturally discontinuous in time when the recorded frame rate is low. This paper reviews the first AIM challenge on video temporal super-resolution (frame interpolation) with a focus on the proposed solutions and results. From low-frame-rate (15 fps) video sequences, the challenge participants are asked to submit higher-frame-rate (60 fps) video sequences by estimating temporally intermediate frames. We employ the REDS-VTSR dataset derived from diverse videos captured in a hand-held camera for training and evaluation purposes. The competition had 62 registered participants, and a total of 8 teams competed in the final testing phase. The challenge winning methods achieve the state-of-the-art in video temporal super-resolution.

AB - Videos contain various types and strengths of motions that may look unnaturally discontinuous in time when the recorded frame rate is low. This paper reviews the first AIM challenge on video temporal super-resolution (frame interpolation) with a focus on the proposed solutions and results. From low-frame-rate (15 fps) video sequences, the challenge participants are asked to submit higher-frame-rate (60 fps) video sequences by estimating temporally intermediate frames. We employ the REDS-VTSR dataset derived from diverse videos captured in a hand-held camera for training and evaluation purposes. The competition had 62 registered participants, and a total of 8 teams competed in the final testing phase. The challenge winning methods achieve the state-of-the-art in video temporal super-resolution.

KW - Frame interpolation

KW - Video frame interpolation

KW - Video temporal super resolution

UR - https://www.scopus.com/pages/publications/85082501673

U2 - 10.1109/ICCVW.2019.00421

DO - 10.1109/ICCVW.2019.00421

M3 - 会议稿件

AN - SCOPUS:85082501673

T3 - Proceedings - 2019 International Conference on Computer Vision Workshop, ICCVW 2019

SP - 3388

EP - 3398

BT - Proceedings - 2019 International Conference on Computer Vision Workshop, ICCVW 2019

PB - Institute of Electrical and Electronics Engineers Inc.

Y2 - 27 October 2019 through 28 October 2019

ER -

Nah S, Son S, Timofte R, Lee KM, Siyao L, Pan Z et al. AIM 2019 challenge on video temporal super-resolution: Methods and results. In Proceedings - 2019 International Conference on Computer Vision Workshop, ICCVW 2019. Institute of Electrical and Electronics Engineers Inc. 2019. p. 3388-3398. 9022180. (Proceedings - 2019 International Conference on Computer Vision Workshop, ICCVW 2019). doi: 10.1109/ICCVW.2019.00421

AIM 2019 challenge on video temporal super-resolution: Methods and results

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this