arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1907.13622cs.CV
收藏

线阵摄像机的视频拼接

Video Stitching for Linear Camera Arrays

University of California, Merced(加州大学默塞德分校);NVIDIA(英伟达)

Wei-Sheng Lai, Orazio Gallo, Jinwei Gu, Deqing Sun, Ming-Hsuan Yang, Jan Kautz

摘要:

尽管图像和视频拼接研究的历史悠久,但现有的学术和商业解决方案仍然会产生强烈的伪影。在这项工作中,我们提出了一个宽基线视频拼接算法的线性相机阵列,是时间稳定和宽容的强视差。我们的关键见解是,拼接可以被视为学习输入视频之间的平滑空间插值的问题。为了解决这个问题,受推扫式摄像机的启发,我们引入了一个快速推扫式插值层,并提出了一种新的推扫式拼接网络,它学习了一个稠密的流场,以平滑地对齐多个输入视频进行空间插值。我们的方法优于国家的最先进的一个显着的利润率,因为我们显示与用户研究,并在许多领域,如虚拟现实,沉浸式远程呈现,自动驾驶和视频监控的直接应用。

英文摘要:

Despite the long history of image and video stitching research, existing academic and commercial solutions still produce strong artifacts. In this work, we propose a wide-baseline video stitching algorithm for linear camera arrays that is temporally stable and tolerant to strong parallax. Our key insight is that stitching can be cast as a problem of learning a smooth spatial interpolation between the input videos. To solve this problem, inspired by pushbroom cameras, we introduce a fast pushbroom interpolation layer and propose a novel pushbroom stitching network, which learns a dense flow field to smoothly align the multiple input videos for spatial interpolation. Our approach outperforms the state-of-the-art by a significant margin, as we show with a user study, and has immediate applications in many areas such as virtual reality, immersive telepresence, autonomous driving, and video surveillance.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑