Re-cinematography

Author:

Gleicher Michael L.1,Liu Feng1

Affiliation:

1. University of Wisconsin-Madison, Madison, WI

Abstract

This article presents an approach to postprocessing casually captured videos to improve apparent camera movement. Re-cinematography transforms each frame of a video such that the video better follows cinematic conventions. The approach breaks a video into shorter segments. Segments of the source video where there is no intentional camera movement are made to appear as if the camera is completely static. For segments with camera motions, camera paths are keyframed automatically and interpolated with matrix logarithms to give velocity-profiled movements that appear intentional and directed. Closeups are inserted to provide compositional variety in otherwise uniform segments. The approach automatically balances the tradeoff between motion smoothness and distortion to the original imagery. Results from our prototype show improvements to poor quality home videos.

Funder

Division of Information and Intelligent Systems

Publisher

Association for Computing Machinery (ACM)

Subject

Computer Networks and Communications,Hardware and Architecture

Reference53 articles.

1. Modeling intent for home video repurposing

2. IMCE

3. Linear combination of transformations

4. Ang T. 2005. Digital Video Handbook. Dorling Kindersley. Ang T. 2005. Digital Video Handbook. Dorling Kindersley.

Cited by 84 articles. 订阅此论文施引文献 订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献

1. Blind 3D Video Stabilization with Spatio-Temporally Varying Motion Blur;ACM Transactions on Multimedia Computing, Communications, and Applications;2024-08-08

2. Sistema de bajo costo para la autoproducción y análisis de vídeos de baloncesto: un caso de estudio para campus universitarios;Campus Virtuales;2024-07-31

3. Video stabilization based on low‐rank constraint and trajectory optimization;IET Image Processing;2024-02-24

4. Minimum Latency Deep Online Video Stabilization;2023 IEEE/CVF International Conference on Computer Vision (ICCV);2023-10-01

5. Content-Preserving Warps for 3D Video Stabilization;Seminal Graphics Papers: Pushing the Boundaries, Volume 2;2023-08

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