# DTSGAN: Learning Dynamic Textures via Spatiotemporal Generative Adversarial Network

arXiv: https://arxiv.org/abs/2412.16948 · HTML: https://mlsanity.com/paper/2412.16948/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 20 references that are in the map.
- First posted on arXiv 22 Dec 2024.

## Builds on (most cited first, 9 of 9)

- [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://mlsanity.com/paper/1502.03167/) (2015)
- [Large Scale GAN Training for High Fidelity Natural Image Synthesis](https://mlsanity.com/paper/1809.11096/) (2018)
- [Improved Training of Wasserstein GANs](https://mlsanity.com/paper/1704.00028/) (2017)
- [MoCoGAN: Decomposing Motion and Content for Video Generation](https://mlsanity.com/paper/1707.04993/) (2017)
- [Generating Videos with Scene Dynamics](https://mlsanity.com/paper/1609.02612/) (2016)
- [SinGAN: Learning a Generative Model from a Single Natural Image](https://mlsanity.com/paper/1905.01164/) (2019)
- [Learning Dynamic Generator Model by Alternating Back-Propagation Through Time](https://mlsanity.com/paper/1812.10587/) (2018)
- [Two-Stream Convolutional Networks for Dynamic Texture Synthesis](https://mlsanity.com/paper/1706.06982/) (2017)
- [Synthesising Dynamic Textures using Convolutional Neural Networks](https://mlsanity.com/paper/1702.07006/) (2017)

## Built on by (most cited first, 3 of 3)

- [CoC-VLA: Delving into Adversarial Domain Transfer for Explainable Autonomous Driving via Chain-of-Causality Visual-Language-Action Model](https://mlsanity.com/paper/2511.19914/) (2025)
- [Human-AI Co-Creation: A Framework for Collaborative Design in Intelligent Systems](https://mlsanity.com/paper/2507.17774/) (2025)
- [Generating Multimodal Images with GAN: Integrating Text, Image, and Style](https://mlsanity.com/paper/2501.02167/) (2025)

## Abstract (arXiv)

Dynamic texture synthesis aims to generate sequences that are visually similar to a reference video texture and exhibit specific stationary properties in time. In this paper, we introduce a spatiotemporal generative adversarial network (DTSGAN) that can learn from a single dynamic texture by capturing its motion and content distribution. With the pipeline of DTSGAN, a new video sequence is generated from the coarsest scale to the finest one. To avoid mode collapse, we propose a novel strategy for data updates that helps improve the diversity of generated results. Qualitative and quantitative experiments show that our model is able to generate high quality dynamic textures and natural motion.