학술논문
AIM 2019 Challenge on Video Temporal Super-Resolution: Methods and Results
Document Type
Conference
Author
Nah, Seungjun; Son, Sanghyun; Timofte, Radu; Lee, Kyoung Mu; Siyao, Li; Pan, Ze; Xu, Xiangyu; Sun, Wenxiu; Choi, Myungsub; Kim, Heewon; Han, Bohyung; Xu, Ning; Park, Bumjun; Yu, Songhyun; Kim, Sangmin; Jeong, Jechang; Shen, Wang; Bao, Wenbo; Zhai, Guangtao; Chen, Li; Gaon, Zhiyong; Chen, Guannan; Lu, Yunhua; Duan, Ran; Liu, Tong; Zhang, Lijie; Park, Woonsung; Kim, Munchurl; Pisha, George; Naor, Eyal; Aloni, Lior
Source
2019 IEEE/CVF International Conference on Computer Vision Workshop (ICCVW) ICCVW Computer Vision Workshop (ICCVW), 2019 IEEE/CVF International Conference on. :3388-3398 Oct, 2019
Subject
Language
ISSN
2473-9944
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.