1. [Publications](/publications)
2. Video Stitching for Linear Camera Arrays
 
 # Video Stitching for Linear Camera Arrays

  ![](/sites/default/files/styles/wide/public/publications/stitching_red.jpg?itok=LmX6Or2C)

 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.



 ## Authors



Wei-Sheng Lai (UC Merced)

Orazio Gallo (NVIDIA)

[Jinwei Gu](/person/jinwei-gu)

Deqing Sun (NVIDIA)

Ming-Hsuan Yang (UC Merced)

[Jan Kautz](/person/jan-kautz)

 

 

 ## Publication Date



Monday, September 9, 2019

 

 ## Published in



[British Machine Vision Conference](https://bmvc2019.org/)

 

 ## Research Area



[Artificial Intelligence and Machine Learning ](/research-area/machine-learning-artificial-intelligence)

[Computational Photography and Imaging](/research-area/computational-photography-imaging)

[Computer Vision](/research-area/computer-vision)

 

 

 ## External Links



[Paper on arXiv](https://arxiv.org/abs/1907.13622)

[Project's webpage](http://vllab.ucmerced.edu/wlai24/video_stitching/)