# Non-Adversarial Video Synthesis with Learned Priors

arXiv: https://arxiv.org/abs/2003.09565 · HTML: https://mlsanity.com/paper/2003.09565/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 21 Mar 2020.

## Built on by (most cited first, 13 of 13)

- [StyleGAN-V: A Continuous Video Generator with the Price, Image Quality and Perks of StyleGAN2](https://mlsanity.com/paper/2112.14683/) (2021)
- [Spatio-Temporal Representation Factorization for Video-based Person Re-Identification](https://mlsanity.com/paper/2107.11878/) (2021)
- [Adversarial Attacks on Black Box Video Classifiers: Leveraging the Power of Geometric Transformations](https://mlsanity.com/paper/2110.01823/) (2021)
- [Cross-Domain Video Anomaly Detection without Target Domain Adaptation](https://mlsanity.com/paper/2212.07010/) (2022)
- [3D-Aware Video Generation](https://mlsanity.com/paper/2206.14797/) (2022)
- [GAMA: Generative Adversarial Multi-Object Scene Attacks](https://mlsanity.com/paper/2209.09502/) (2022)
- [StyleFaceV: Face Video Generation via Decomposing and Recomposing Pretrained StyleGAN3](https://mlsanity.com/paper/2208.07862/) (2022)
- [Leveraging Local Patch Differences in Multi-Object Scenes for Generative Adversarial Attacks](https://mlsanity.com/paper/2209.09883/) (2022)
- [MotionVideoGAN: A Novel Video Generator Based on the Motion Space Learned from Image Pairs](https://mlsanity.com/paper/2303.02906/) (2023)
- [ArrowGAN : Learning to Generate Videos by Learning Arrow of Time](https://mlsanity.com/paper/2101.03710/) (2021)
- [Video Reenactment as Inductive Bias for Content-Motion Disentanglement](https://mlsanity.com/paper/2102.00324/) (2021)
- [Ada-VSR: Adaptive Video Super-Resolution with Meta-Learning](https://mlsanity.com/paper/2108.02832/) (2021)
- [Poisson2Sparse: Self-Supervised Poisson Denoising From a Single Image](https://mlsanity.com/paper/2206.01856/) (2022)

## Abstract (arXiv)

Most of the existing works in video synthesis focus on generating videos using adversarial learning. Despite their success, these methods often require input reference frame or fail to generate diverse videos from the given data distribution, with little to no uniformity in the quality of videos that can be generated. Different from these methods, we focus on the problem of generating videos from latent noise vectors, without any reference input frames. To this end, we develop a novel approach that jointly optimizes the input latent space, the weights of a recurrent neural network and a generator through non-adversarial learning. Optimizing for the input latent space along with the network weights allows us to generate videos in a controlled environment, i.e., we can faithfully generate all videos the model has seen during the learning process as well as new unseen videos. Extensive experiments on three challenging and diverse datasets well demonstrate that our approach generates superior quality videos compared to the existing state-of-the-art methods.