3 Hits in 1.8 sec

DTVNet+: A High-Resolution Scenic Dataset for Dynamic Time-lapse Video Generation [article]

Jiangning Zhang, Chao Xu, Yong Liu, Yunliang Jiang
2021 arXiv   pre-print
This paper presents a novel end-to-end dynamic time-lapse video generation framework, named DTVNet, to generate diversified time-lapse videos from a single landscape image conditioned on normalized motion  ...  The proposed DTVNet consists of two submodules: Optical Flow Encoder (OFE) and Dynamic Video Generator (DVG).  ...  METHOD In this paper, a novel end-to-end dynamic time-lapse video generation framework named DTVNet is proposed to generate diversified time-lapse videos from a single landscape image.  ... 
arXiv:2008.04776v2 fatcat:z3efsr5ga5btlf3cfwnvqiuzsa

A Good Image Generator Is What You Need for High-Resolution Video Synthesis [article]

Yu Tian, Jian Ren, Menglei Chai, Kyle Olszewski, Xi Peng, Dimitris N. Metaxas, Sergey Tulyakov
2021 arXiv   pre-print
Image and video synthesis are closely related areas aiming at generating content from noise.  ...  We present a framework that leverages contemporary image generators to render high-resolution videos.  ...  We compare our method with DTVNet on the video prediction task. The testing set of Sky Time-lapse dataset includes 2, 815 short video clips.  ... 
arXiv:2104.15069v1 fatcat:f3m3izfjhncr3e4dncysd7v4oq

Stochastic Image-to-Video Synthesis using cINNs [article]

Michael Dorkenwald, Timo Milbich, Andreas Blattmann, Robin Rombach, Konstantinos G. Derpanis, Björn Ommer
2021 arXiv   pre-print
In contrast to common stochastic image-to-video synthesis, such a model does not merely generate arbitrary videos progressing the initial image.  ...  Video understanding calls for a model to learn the characteristic interplay between static scene content and its dynamics: Given an image, the model must be able to predict a future progression of the  ...  Landscape [87] consists of ∼ 3000 time-lapse videos of dynamic sky scenes, e.g., cloudy skies and night scenes with moving stars.  ... 
arXiv:2105.04551v2 fatcat:sye4z4og6vfghardh3edxsc7pi