AIM 2019 Challenge on Video Extreme Super-Resolution: Methods and Results

被引：1

作者：

Fuoli, Dario ^{[1
]}

Gu, Shuhang ^{[1
]}

Timofte, Radu ^{[1
]}

Tao, Xin ^{[2
]}

Li, Wenbo ^{[2
]}

Guo, Taian ^{[2
]}

Deng, Zijun ^{[2
]}

Lu, Liying ^{[2
]}

Dai, Tao ^{[2
]}

Shen, Xiaoyong ^{[2
]}

Xia, Shutao ^{[2
]}

Dai, Yurong ^{[2
]}

Jia, Jiaya ^{[2
]}

Yi, Peng ^{[3
]}

Wang, Zhongyuan ^{[3
]}

Jiang, Kui ^{[3
]}

Jiang, Junjun ^{[3
]}

Ma, Jiayi ^{[3
]}

Zhong, Zhiwei ^{[4
]}

Wang, Chenyang ^{[4
]}

Jiang, JunJun ^{[4
]}

Liu, Xianming ^{[4
]}

机构：

[1] Swiss Fed Inst Technol, Comp Vis Lab, Zurich, Switzerland

[2] Tecent X Lab, Shenzhen, Guangdong, Peoples R China

[3] Wuhan Univ, Sch Comp Sci, Natl Engn Res Ctr Multimedia Software, Wuhan, Peoples R China

[4] Harbin Inst Technol, Harbin 150001, Peoples R China

来源：

2019 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION WORKSHOPS (ICCVW) | 2019年

关键词：

D O I：

10.1109/ICCVW.2019.00430

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

This paper reviews the video extreme super-resolution challenge associated with the AIM 2019 workshop, with emphasis on submitted solutions and results. Video extreme super-resolution (x16) is a highly challenging problem, because 256 pixels need to be estimated for each single pixel in the low-resolution (LR) input. Contrary to single image super-resolution (SISR), video provides temporal information, which can be additionally leveraged to restore the heavily downscaled videos and is imperative for any video super-resolution (VSR) method. The challenge is composed of two tracks, to find the best performing method for fully supervised VSR (track 1) and to find the solution which generates the perceptually best looking outputs (track 2). A new video dataset, called Vid3oC, is introduced together with the challenge.

引用

页码：3467 / 3475

页数：9

共 41 条

[1]

[Anonymous], 2017, IEEE C COMP VIS PATT

[2]

[Anonymous], 2017, SPARSE REPRESENTATIO

[3]

[Anonymous], 2017, IEEE C COMP VIS PATT

[4]

[Anonymous], 2018, IEEE C COMP VIS PATT

[5] Maximum a Posteriori Video Super-Resolution Using a New Multichannel Image Prior [J].

Belekos, Stefanos P. ;

Galatsanos, Nikolaos P. ;

Katsaggelos, Aggelos K. .

IEEE TRANSACTIONS ON IMAGE PROCESSING, 2010, 19 (06) :1451-1464

[6] A New Adaptive Video Super-Resolution Algorithm With Improved Robustness to Innovations [J].

Borsoi, Ricardo Augusto ;

Costa, Guilherme Holsbach ;

Moreira Bermudez, Jose Carlos .

IEEE TRANSACTIONS ON IMAGE PROCESSING, 2019, 28 (02) :673-686

[7]

Caballero J., 2017, IEEE C COMP VIS PATT

[8]

Courtney PG, 2015, IEEE COMP SEMICON

[9] Pixel Recursive Super Resolution [J].

Dahl, Ryan ;

Norouzi, Mohammad ;

Shlens, Jonathon .

2017 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV), 2017, :5449-5458

[10] Sparse Representation-Based Multiple Frame Video Super-Resolution [J].

Dai, Qiqin ;

Yoo, Seunghwan ;

Kappeler, Armin ;

Katsaggelos, Aggelos K. .

IEEE TRANSACTIONS ON IMAGE PROCESSING, 2017, 26 (02) :765-781

← 1 2 3 4 5 →