# Learning Long-Term Style-Preserving Blind Video Temporal Consistency

arXiv: https://arxiv.org/abs/2103.07278 · HTML: https://mlsanity.com/paper/2103.07278/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 16 references that are in the map.
- First posted on arXiv 12 Mar 2021.

## Builds on (most cited first, 8 of 8)

- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [Convolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcasting](https://mlsanity.com/paper/1506.04214/) (2015)
- [SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size](https://mlsanity.com/paper/1602.07360/) (2016)
- [FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networks](https://mlsanity.com/paper/1612.01925/) (2016)
- [Learning Blind Video Temporal Consistency](https://mlsanity.com/paper/1808.00449/) (2018)
- [Arbitrary Style Transfer with Style-Attentional Networks](https://mlsanity.com/paper/1812.02342/) (2018)
- [Optical Flow Distillation: Towards Efficient and Stable Video Style Transfer](https://mlsanity.com/paper/2007.05146/) (2020)

## Built on by (most cited first, 5 of 5)

- [Deep Graphics Encoder for Real-Time Video Makeup Synthesis from Example](https://mlsanity.com/paper/2105.06407/) (2021)
- [Real-time Virtual-Try-On from a Single Example Image through Deep Inverse Graphics and Learned Differentiable Renderers](https://mlsanity.com/paper/2205.06305/) (2022)
- [Task Agnostic Restoration of Natural Video Dynamics](https://mlsanity.com/paper/2206.03753/) (2022)
- [Interactive Control over Temporal Consistency while Stylizing Video Streams](https://mlsanity.com/paper/2301.00750/) (2023)
- [BlazeBVD: Make Scale-Time Equalization Great Again for Blind Video Deflickering](https://mlsanity.com/paper/2403.06243/) (2024)

## Abstract (arXiv)

When trying to independently apply image-trained algorithms to successive frames in videos, noxious flickering tends to appear. State-of-the-art post-processing techniques that aim at fostering temporal consistency, generate other temporal artifacts and visually alter the style of videos. We propose a postprocessing model, agnostic to the transformation applied to videos (e.g. style transfer, image manipulation using GANs, etc.), in the form of a recurrent neural network. Our model is trained using a Ping Pong procedure and its corresponding loss, recently introduced for GAN video generation, as well as a novel style preserving perceptual loss. The former improves long-term temporal consistency learning, while the latter fosters style preservation. We evaluate our model on the DAVIS and videvo.net datasets and show that our approach offers state-of-the-art results concerning flicker removal, and better keeps the overall style of the videos than previous approaches.