Blind 3D Video Stabilization with Spatio-Temporally Varying Motion Blur

Author:

Li Hengwei1ORCID,Wang Wei1ORCID,Wang Xiao1ORCID,Yuan Xin1ORCID,Xu Xin1ORCID

Affiliation:

1. School of Computer Science and Technology and Hubei Province Key Laboratory of Intelligent Information Processing and Real-time Industrial System, Wuhan University of Science and Technology, China

Abstract

Video stabilization is a challenging task that attempts to compensate for the overall frame shake during video acquisition. Existing 3D video stabilization methods aim at modeling camera perspective projection through either data-driven training or explicit motion estimation. However, the above methods are difficult to effectively solve the issue of shaky videos with abrupt object movements, resulting in local motion blur in the direction of the movement. This phenomenon is prevalent in real-world scenarios featuring foreground blind motion scenes. Unfortunately, directly combining stabilization and deblurring methods poses challenges when dealing with this situation. In the video, the intensity of motion blur undergoes continuous changes, and the direct combination method inadequately utilizes spatiotemporal information, providing insufficient clues for cross-frame compensation. To alleviate this problem, the Cross-frame-temporal Module framework is proposed to address blind motion blur induced by various conditions, which utilizes cross-frame temporal features to estimate depth maps and camera motion. In this framework, a B lur T ransform N etwork (BTNet) is designed to adapt to spatially varying motion blur, which transforms local regions according to the impact of blur intensities to adapt to the effects of non-uniform motion blur; furthermore, our T emporal- a ware N etwork (TANet) further suppresses motion blur by leveraging cross-frame temporal features. In addition, the limited availability of pair-training video data containing motion blur limits the application of this approach in practice. The Cross-frame-temporal Module framework adopts an un-pretrained in-test training strategy. Extensive experimental results have demonstrated that our method outperforms state-of-the-art methods.

Publisher

Association for Computing Machinery (ACM)

Reference51 articles.

1. Muhammad Kashif Ali, Sangjoon Yu, and Tae Hyun Kim. 2020. Deep motion blind video stabilization. arXiv preprint arXiv:2011.09697 (2020).

2. Video anomaly detection with multi-scale feature and temporal information fusion

3. Guillermo Carbajal, Patricia Vitoria, Mauricio Delbracio, Pablo Musé, and José Lezama. 2021. Non-uniform blur kernel estimation via adaptive basis decomposition. arXiv preprint arXiv:2102.01026 (2021).

4. Jierun Chen, Shiu-hong Kao, Hao He, Weipeng Zhuo, Song Wen, Chul-Ho Lee, and S-H Gary Chan. 2023. Run, Don’t Walk: Chasing Higher FLOPS for Faster Neural Networks. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 12021–12031.

5. Yu-Ta Chen, Kuan-Wei Tseng, Yao-Chih Lee, Chun-Yu Chen, and Yi-Ping Hung. 2021. Pixstabnet: Fast multi-scale deep online video stabilization with pixel-based warping. In 2021 IEEE International Conference on Image Processing (ICIP). IEEE, 1929–1933.

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3