Animating still natural images using warping

Thi-Ngoc-Hanh Le, Chih-Kuo Yeh, Ying-Chi Lin, and Tong-Yee Lee

CGVSL - National Cheng-Kung University



Abstract


From a single still image, a looping video could be generated by imparting subtle motion to objects in the image. The results are a hybrid of photography and video. They contain gentle motion in some objects, while the rest of the image remains still. Existing techniques are successful in animating such images. However, there are still some drawbacks needed to investigate, such as the demand on a huge computation time in retrieving the matched videos, or the challenges in controlling the desired motion not only in terms of a single region but also in terms of consistency in regions. In this work, we address these issues by proposing an interactive system with a novel warping method. The key idea of our approach is to utilize user's annotations to impart motion to certain objects. With two proposed phases in terms of preserve-curve-warping and cycle warping, a looping video is generated. We demonstrate the effectiveness of our method via various experimental results and evaluations. We show that with a simple and lightweight method, our system is able to deal with the animating still image's problems and achieves realistic motion and appealing videos. In addition, our proposed system is easy to create plausible animation using simple user annotations without referencing to video database or machine learning models and allows ordinary users with minimal expertise to explore compelling results.


Keywords -- animation, still images, cycle warping, warping, preserve curve warping


BibTeX

@article{le2022animating, title={Animating still natural images using warping},
author={Le, Thi-Ngoc-Hanh and Yeh, Chih-Kuo and Lin, Ying-Chi and Lee, Tong-Yee},
journal={ACM Transactions on Multimedia Computing, Communications, and Applications (TOMM)},
year={2022},
publisher={ACM New York, NY}
}

Grant

This work was supported in part by the Ministry of Science and Technology (under nos. 108-2221-E-006-038-MY3 and 110-2221-E-006-135-MY3), Taiwan, Republic of China and the Key Area Research Program of Universities in Guangdong Province (Nature science), China (under no. 2020KQNCX095)

Demo video


Results




Still image - Waterfall


Still image - BanGioc Waterfall


Still image - Abstract painting


Still image - Body of water


Still image - IguazeFalls


Still image - Cross river


Still image - River at night


Still image - Starry night


Still image - Roma


Still image - Nature Scene


Still image - Tahquamenon Falls


Still image - Artist Splash


Still image - Cycle Splash


Still image - Women Splash