# Two-Stream Convolutional Networks for Dynamic Texture Synthesis

arXiv: https://arxiv.org/abs/1706.06982 · HTML: https://mlsanity.com/paper/1706.06982/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 21 Jun 2017.

## Built on by (most cited first, 15 of 15)

- [Stochastic Image-to-Video Synthesis using cINNs](https://mlsanity.com/paper/2105.04551/) (2021)
- [DyNCA: Real-time Dynamic Texture Synthesis Using Neural Cellular Automata](https://mlsanity.com/paper/2211.11417/) (2022)
- [Mesh Neural Cellular Automata](https://mlsanity.com/paper/2311.02820/) (2023)
- [Endless Loops: Detecting and Animating Periodic Patterns in Still Images](https://mlsanity.com/paper/2105.09374/) (2021)
- [Water Simulation and Rendering from a Still Photograph](https://mlsanity.com/paper/2210.02553/) (2022)
- [Dynamic Texture Synthesis by Incorporating Long-range Spatial and Temporal Correlations](https://mlsanity.com/paper/2104.05940/) (2021)
- [Dynamic Texture Transfer using PatchMatch and Transformers](https://mlsanity.com/paper/2402.00606/) (2024)
- [StyleCineGAN: Landscape Cinemagraph Generation using a Pre-trained StyleGAN](https://mlsanity.com/paper/2403.14186/) (2024)
- [DTSGAN: Learning Dynamic Textures via Spatiotemporal Generative Adversarial Network](https://mlsanity.com/paper/2412.16948/) (2024)
- [CAMS: Color-Aware Multi-Style Transfer](https://mlsanity.com/paper/2106.13920/) (2021)
- [A spatiotemporal style transfer algorithm for dynamic visual stimulus generation](https://mlsanity.com/paper/2403.04940/) (2024)
- [Infusion: internal diffusion for inpainting of dynamic textures and complex motion](https://mlsanity.com/paper/2311.01090/) (2023)
- [Emergent Dynamics in Neural Cellular Automata](https://mlsanity.com/paper/2404.06406/) (2024)
- [Neural Differential Appearance Equations](https://mlsanity.com/paper/2410.07128/) (2024)
- [Physics-Guided Motion Loss for Video Generation Model](https://mlsanity.com/paper/2506.02244/) (2025)

## Abstract (arXiv)

We introduce a two-stream model for dynamic texture synthesis. Our model is based on pre-trained convolutional networks (ConvNets) that target two independent tasks: (i) object recognition, and (ii) optical flow prediction. Given an input dynamic texture, statistics of filter responses from the object recognition ConvNet encapsulate the per-frame appearance of the input texture, while statistics of filter responses from the optical flow ConvNet model its dynamics. To generate a novel texture, a randomly initialized input sequence is optimized to match the feature statistics from each stream of an example texture. Inspired by recent work on image style transfer and enabled by the two-stream model, we also apply the synthesis approach to combine the texture appearance from one texture with the dynamics of another to generate entirely novel dynamic textures. We show that our approach generates novel, high quality samples that match both the framewise appearance and temporal evolution of input texture. Finally, we quantitatively evaluate our texture synthesis approach with a thorough user study.