# DeepLandscape: Adversarial Modeling of Landscape Video

arXiv: https://arxiv.org/abs/2008.09655 · HTML: https://mlsanity.com/paper/2008.09655/

## Key facts

- Cited by 17 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 21 Aug 2020.

## Built on by (most cited first, 17 of 17)

- [GAN Inversion: A Survey](https://mlsanity.com/paper/2101.05278/) (2021)
- [StylePeople: A Generative Model of Fullbody Human Avatars](https://mlsanity.com/paper/2104.08363/) (2021)
- [Stochastic Image-to-Video Synthesis using cINNs](https://mlsanity.com/paper/2105.04551/) (2021)
- [Controllable Animation of Fluid Elements in Still Images](https://mlsanity.com/paper/2112.03051/) (2021)
- [Detecting Images Generated by Deep Diffusion Models using their Local Intrinsic Dimensionality](https://mlsanity.com/paper/2307.02347/) (2023)
- [3D Cinemagraphy from a Single Image](https://mlsanity.com/paper/2303.05724/) (2023)
- [LaMD: Latent Motion Diffusion for Image-Conditional Video Generation](https://mlsanity.com/paper/2304.11603/) (2023)
- [Text-Guided Synthesis of Eulerian Cinemagraphs](https://mlsanity.com/paper/2307.03190/) (2023)
- [Blowing in the Wind: CycleNet for Human Cinemagraphs from Still Images](https://mlsanity.com/paper/2303.08639/) (2023)
- [RIGID: Recurrent GAN Inversion and Editing of Real Face Videos](https://mlsanity.com/paper/2308.06097/) (2023)
- [Advances in 3D Neural Stylization: A Survey](https://mlsanity.com/paper/2311.18328/) (2023)
- [Learning Fine-Grained Motion Embedding for Landscape Animation](https://mlsanity.com/paper/2109.02216/) (2021)
- [Optimizing 4D Gaussians for Dynamic Scene Video from Single Landscape Images](https://mlsanity.com/paper/2504.05458/) (2025)
- [Disentangling Random and Cyclic Effects in Time-Lapse Sequences](https://mlsanity.com/paper/2207.01413/) (2022)
- [StyLandGAN: A StyleGAN based Landscape Image Synthesis using Depth-map](https://mlsanity.com/paper/2205.06611/) (2022)
- [Sketch-Guided Stylized Landscape Cinemagraph Synthesis](https://mlsanity.com/paper/2412.00638/) (2024)
- [LivingWorld: Interactive 4D World Generation with Environmental Dynamics](https://mlsanity.com/paper/2604.01641/) (2026)

## Abstract (arXiv)

We build a new model of landscape videos that can be trained on a mixture of static landscape images as well as landscape animations. Our architecture extends StyleGAN model by augmenting it with parts that allow to model dynamic changes in a scene. Once trained, our model can be used to generate realistic time-lapse landscape videos with moving objects and time-of-the-day changes. Furthermore, by fitting the learned models to a static landscape image, the latter can be reenacted in a realistic way. We propose simple but necessary modifications to StyleGAN inversion procedure, which lead to in-domain latent codes and allow to manipulate real images. Quantitative comparisons and user studies suggest that our model produces more compelling animations of given photographs than previously proposed methods. The results of our approach including comparisons with prior art can be seen in supplementary materials and on the project page https://saic-mdal.github.io/deep-landscape