Learning to Generate Time-Lapse Videos Using Multi-Stage Dynamic Generative Adversarial Networks
Abstract
A GAN-based two-stage method generates realistic high-resolution time-lapse videos by predicting future frames and refining motion dynamics with a Gram matrix.
Taking a photo outside, can we predict the immediate future, e.g., how would the cloud move in the sky? We address this problem by presenting a generative adversarial network (GAN) based two-stage approach to generating realistic time-lapse videos of high resolution. Given the first frame, our model learns to generate long-term future frames. The first stage generates videos of realistic contents for each frame. The second stage refines the generated video from the first stage by enforcing it to be closer to real videos with regard to motion dynamics. To further encourage vivid motion in the final generated video, Gram matrix is employed to model the motion more precisely. We build a large scale time-lapse dataset, and test our approach on this new dataset. Using our model, we are able to generate realistic videos of up to 128times 128 resolution for 32 frames. Quantitative and qualitative experiment results have demonstrated the superiority of our model over the state-of-the-art models.
Get this paper in your agent:
hf papers read 1709.07592 Don't have the latest CLI?
curl -LsSf https://hf.co/cli/install.sh | bash Models citing this paper 0
No model linking this paper
Datasets citing this paper 0
No dataset linking this paper
Spaces citing this paper 0
No Space linking this paper
Collections including this paper 0
No Collection including this paper