Test-Time Adaptation for Video Frame Interpolation via Meta-Learning
- Authors
- Choi, Myungsub; Choi, Janghoon; Baik, Sungyong; Kim, Tae Hyun; Lee, Kyoung Mu
- Issue Date
- Dec-2022
- Publisher
- IEEE COMPUTER SOC
- Keywords
- Interpolation; Adaptation models; Estimation; Task analysis; Visualization; Superresolution; Performance gain; Video frame interpolation; test-time adaptation; meta-learning; slow motion; self-supervision; image synthesis; MAML
- Citation
- IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, v.44, no.12, pp.9615 - 9628
- Indexed
- SCIE
SCOPUS
- Journal Title
- IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
- Volume
- 44
- Number
- 12
- Start Page
- 9615
- End Page
- 9628
- URI
- https://scholarworks.bwise.kr/hanyang/handle/2021.sw.hanyang/172787
- DOI
- 10.1109/TPAMI.2021.3129819
- ISSN
- 0162-8828
- Abstract
- Video frame interpolation is a challenging problem that involves various scenarios depending on the variety of foreground and background motions, frame rate, and occlusion. Therefore, generalizing across different scenes is difficult for a single network with fixed parameters. Ideally, one could have a different network for each scenario, but this will be computationally infeasible for practical applications. In this work, we propose MetaVFI, an adaptive video frame interpolation algorithm that uses additional information readily available at test time but has not been exploited in previous works. We initially show the benefits of test-time adaptation through simple fine-tuning of a network and then greatly improve its efficiency by incorporating meta-learning. Thus, we obtain significant performance gains with only a single gradient update without introducing any additional parameters. Moreover, the proposed MetaVFI algorithm is model-agnostic which can be easily combined with any video frame interpolation network. We show that our adaptive framework greatly improves the performance of baseline video frame interpolation networks on multiple benchmark datasets.
- Files in This Item
-
Go to Link
- Appears in
Collections - 서울 공과대학 > 서울 컴퓨터소프트웨어학부 > 1. Journal Articles
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.