# End-to-End Time-Lapse Video Synthesis from a Single Outdoor Image

arXiv: https://arxiv.org/abs/1904.00680 · HTML: https://mlsanity.com/paper/1904.00680/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 1 Apr 2019.

## Built on by (most cited first, 12 of 12)

- [Diffusion Probabilistic Modeling for Video Generation](https://mlsanity.com/paper/2203.09481/) (2022)
- [NeRF for Outdoor Scene Relighting](https://mlsanity.com/paper/2112.05140/) (2021)
- [DiT4Edit: Diffusion Transformer for Image Editing](https://mlsanity.com/paper/2411.03286/) (2024)
- [FitVid: Overfitting in Pixel-Level Video Prediction](https://mlsanity.com/paper/2106.13195/) (2021)
- [MagicTime: Time-lapse Video Generation Models as Metamorphic Simulators](https://mlsanity.com/paper/2404.05014/) (2024)
- [Self-supervised Outdoor Scene Relighting](https://mlsanity.com/paper/2107.03106/) (2021)
- [Diffusion-Based Visual Art Creation: A Survey and New Perspectives](https://mlsanity.com/paper/2408.12128/) (2024)
- [Learning Fine-Grained Motion Embedding for Landscape Animation](https://mlsanity.com/paper/2109.02216/) (2021)
- [Disentangling Random and Cyclic Effects in Time-Lapse Sequences](https://mlsanity.com/paper/2207.01413/) (2022)
- [Time-of-Day Neural Style Transfer for Architectural Photographs](https://mlsanity.com/paper/2209.05800/) (2022)
- [Memory-guided Image De-raining Using Time-Lapse Data](https://mlsanity.com/paper/2201.01883/) (2022)
- [TimeNeRF: Building Generalizable Neural Radiance Fields across Time from Few-Shot Input Views](https://mlsanity.com/paper/2507.13929/) (2025)

## Abstract (arXiv)

Time-lapse videos usually contain visually appealing content but are often difficult and costly to create. In this paper, we present an end-to-end solution to synthesize a time-lapse video from a single outdoor image using deep neural networks. Our key idea is to train a conditional generative adversarial network based on existing datasets of time-lapse videos and image sequences. We propose a multi-frame joint conditional generation framework to effectively learn the correlation between the illumination change of an outdoor scene and the time of the day. We further present a multi-domain training scheme for robust training of our generative models from two datasets with different distributions and missing timestamp labels. Compared to alternative time-lapse video synthesis algorithms, our method uses the timestamp as the control variable and does not require a reference video to guide the synthesis of the final output. We conduct ablation studies to validate our algorithm and compare with state-of-the-art techniques both qualitatively and quantitatively.