Time Flies: Animating a Still Image with Time-Lapse Video As Reference

Chia Chi Cheng, Hung Yu Chen, Wei-Chen Chiu

Research output: Contribution to journalConference articlepeer-review

1 Scopus citations


Time-lapse videos usually perform eye-catching appearances but are often hard to create. In this paper, we propose a self-supervised end-to-end model to generate the time-lapse video from a single image and a reference video. Our key idea is to extract both the style and the features of temporal variation from the reference video, and transfer them onto the input image. To ensure both the temporal consistency and realness of our resultant videos, we introduce several novel designs in our architecture, including classwise NoiseAdaIN, flow loss, and the video discriminator. In comparison to the baselines of state-of-the-art style transfer approaches, our proposed method is not only efficient in computation but also able to create more realistic and temporally smooth time-lapse video of a still image, with its temporal variation consistent to the reference.

Original languageEnglish
Article number9157536
Pages (from-to)5640-5649
Number of pages10
JournalProceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
StatePublished - 5 Aug 2020
Event2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2020 - Virtual, Online, United States
Duration: 14 Jun 202019 Jun 2020


Dive into the research topics of 'Time Flies: Animating a Still Image with Time-Lapse Video As Reference'. Together they form a unique fingerprint.

Cite this