Deep Motion Blind Video Stabilization
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Ali, Muhammad Kashif | - |
dc.contributor.author | Yu, Sangjoon | - |
dc.contributor.author | Kim, Tae Hyun | - |
dc.date.accessioned | 2023-11-24T03:02:22Z | - |
dc.date.available | 2023-11-24T03:02:22Z | - |
dc.date.created | 2023-11-20 | - |
dc.date.issued | 2021-10 | - |
dc.identifier.issn | 0000-0000 | - |
dc.identifier.uri | https://scholarworks.bwise.kr/hanyang/handle/2021.sw.hanyang/192875 | - |
dc.description.abstract | Despite the advances in the field of generative models in computer vision, video stabilization still lacks a pure regressive deep-learning-based formulation. Deep video stabilization is generally formulated with the help of explicit motion estimation modules due to the lack of a dataset containing pairs of videos with similar perspective but different motion. Therefore, the deep learning approaches for this task have difficulties in the pixel-level synthesis of latent stabilized frames, and resort to motion estimation modules for indirect transformations of the unstable frames to stabilized frames, leading to the loss of visual content near the frame boundaries. In this work, we aim to declutter this over-complicated formulation of video stabilization with the help of a novel dataset that contains pairs of training videos with similar perspective but different motion, and verify its effectiveness by successfully learning motion blind full-frame video stabilization through employing strictly conventional generative techniques and further improve the stability through a curriculum-learning inspired adversarial training strategy. Through extensive experimentation, we show the quantitative and qualitative advantages of the proposed approach to the state-of-the-art video stabilization approaches. Moreover, our method achieves ∼ 3× speed-up over the currently available fastest video stabilization methods. | - |
dc.language | 영어 | - |
dc.language.iso | en | - |
dc.publisher | British Machine Vision Association, BMVA | - |
dc.title | Deep Motion Blind Video Stabilization | - |
dc.type | Article | - |
dc.contributor.affiliatedAuthor | Kim, Tae Hyun | - |
dc.identifier.doi | 10.48550/arXiv.2011.09697 | - |
dc.identifier.scopusid | 2-s2.0-85176123076 | - |
dc.identifier.bibliographicCitation | 32nd British Machine Vision Conference, BMVC 2021, pp.1 - 13 | - |
dc.relation.isPartOf | 32nd British Machine Vision Conference, BMVC 2021 | - |
dc.citation.title | 32nd British Machine Vision Conference, BMVC 2021 | - |
dc.citation.startPage | 1 | - |
dc.citation.endPage | 13 | - |
dc.type.rims | ART | - |
dc.type.docType | Conference paper | - |
dc.description.journalClass | 1 | - |
dc.description.isOpenAccess | N | - |
dc.description.journalRegisteredClass | scopus | - |
dc.subject.keywordPlus | Estimation module | - |
dc.subject.keywordPlus | Generative model | - |
dc.subject.keywordPlus | Indirect transformations | - |
dc.subject.keywordPlus | Learning approach | - |
dc.subject.keywordPlus | Pixel level | - |
dc.subject.keywordPlus | Qualitative advantages | - |
dc.subject.keywordPlus | State of the art | - |
dc.subject.keywordPlus | Training strategy | - |
dc.subject.keywordPlus | Video stabilization | - |
dc.subject.keywordPlus | Visual content | - |
dc.identifier.url | https://www.bmvc2021-virtualconference.com/assets/papers/0316.pdf | - |
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.
222, Wangsimni-ro, Seongdong-gu, Seoul, 04763, Korea+82-2-2220-1365
COPYRIGHT © 2021 HANYANG UNIVERSITY.
Certain data included herein are derived from the © Web of Science of Clarivate Analytics. All rights reserved.
You may not copy or re-distribute this material in whole or in part without the prior written consent of Clarivate Analytics.