Refilming with Depth-Inferred Videos

Guofeng Zhang1       Zilong Dong1       Jiaya Jia2       Liang Wan2       Tien-Tsin Wong2        Hujun Bao1
1State Key Lab of CAD&CG, Zhejiang University                        2The Chinese University of Hong Kong


Abstract-Compared to still image editing, content-based video editing faces the additional challenges of maintaining the spatio-temporal consistency with respect to geometry. This brings up difficulties of seamlessly modifying video content, for instance, inserting or removing an object. In this paper, we present a new video editing system for creating spatio-temporally consistent and visually appealing re-filming effects. Unlike the typical filming practice, our system requires no labor-intensive construction of 3D models/surfaces mimicking the real scene. Instead, it is based on an unsupervised inference of view-dependent depth maps for all video frames. We provide interactive tools requiring only a small amount of user input to perform elementary video content editing, such as separating video layers, completing background scene, and extracting moving objects. These tools can be utilized to produce a variety of visual effects in our system, including but not limited to video composition, ``predator'' effect, bullet-time, depth-of-field, and fog synthesis. Some of the effects can be achieved in real-time.


Refilming with Depth-Inferred Videos
Guofeng Zhang, Zilong Dong, Jiaya Jia, Liang Wan, Tien-Tsin Wong and Hujun Bao
IEEE Transactions on Visualization and Computer Graphics (TVCG), 15(5):828-840,2009.


author = {Guofeng Zhang and Zilong Dong and Jiaya Jia and Liang Wan and Tien-Tsin Wong and Hujun Bao},
title = {Refilming with Depth-Inferred Videos},
journal ={IEEE Transactions on Visualization and Computer Graphics},
volume = {15},
number = {5},
year = {2009},
pages = {828-840},
publisher = {IEEE Computer Society},
address = {Los Alamitos, CA, USA},

Result Movie


Refilming with Depth-Inferred Videos


More Results