Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Fast and Accurate One-Stage Space-Time Video Super-Resolution (accepted in CVPR 2020)
| Date | Stars |
|---|---|
| 2026-07-24 | 932 |
| 2026-07-25 | 932 |
| 2026-07-28 | 932 |
| 2026-07-30 | 932 |
| 2026-08-06 | 932 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
# Zooming-Slow-Mo (CVPR-2020)
By [Xiaoyu Xiang<sup>\*</sup>](https://engineering.purdue.edu/people/xiaoyu.xiang.1), [Yapeng Tian<sup>\*</sup>](http://yapengtian.org/), [Yulun Zhang](http://yulunzhang.com/), [Yun Fu](http://www1.ece.neu.edu/~yunfu/), [Jan P. Allebach<sup>+</sup>](https://engineering.purdue.edu/~allebach/), [Chenliang Xu<sup>+</sup>](https://www.cs.rochester.edu/~cxu22/) (<sup>\*</sup> equal contributions, <sup>+</sup> equal advising)
This is the official Pytorch implementation of _Zooming Slow-Mo: Fast and Accurate One-Stage Space-Time Video Super-Resolution_.
#### [Paper](https://arxiv.org/abs/2002.11616) | [Journal Version](https://arxiv.org/abs/2104.07473) | [Demo (YouTube)](https://youtu.be/8mgD8JxBOus) | [1-min teaser (YouTube)](https://www.youtube.com/watch?v=C1o85AXUNl8) | [1-min teaser (Bilibili)](https://www.bilibili.com/video/BV1GK4y1t7nb/)
<table>
<thead>
<tr>
<td>Input </td>
<td>Output</td>
</tr>
</thead>
<tr>
<td colspan="2">
<a href="https://youtu.be/8mgD8JxBOus">
<img src="dump/demo720.gif" alt="Demo GIF">
</img>
</a>
</td>
</tr>
</table>
## Updates
- 2020.3.13 Add meta-info of datasets used in this paper
- 2020.3.11 Add new function: video converter
- 2020.3.10: Upload the complete code and pretrained models
## Contents
0. [Introduction](#introduction)
1. [Prerequisites](#Prerequisites)
2. [Get Started](#Get-Started)
- [Installation](#Installation)
- [Training](#Training)
- [Testing](#Testing)
- [Colab Notebook](#Colab-Notebook)
3. [Citations](#citations)
4. [Contact](#Contact)
5. [License](#License)
6. [Acknowledgments](#Acknowledgments)
## Introduction
The repository contains the entire project (including all the preprocessing) for one-stage space-time video super-resolution with Zooming Slow-Mo.
Zooming Slow-Mo is a recently proposed joint video frame interpolation (VFI) and video super-resolution (VSR) method, which directly synthesizes an HR slow-motion video from an LFR, LR video. It is going to be published in [CVPR 2020](http://cvpr2020.thecvf.com/). The most up-to-date paper with supplementary materials can be found at [arXiv](https://arxiv.org/abs/2002.11616).
In Zooming Slow-Mo, we firstly temporally interpolate features of the missing LR frame by the proposed feature temporal interpolation network. Then, we propose a deformable ConvLSTM to align and aggregate temporal information simultaneously. Finally, a deep reconstruction network is adopted to predict HR slow-motion video frames. If our proposed architectures also help your research, please consider citing our paper.
Zooming Slow-Mo achieves state-of-the-art performance by PSNR and SSIM in Vid4, Vimeo test sets.
## Prerequisites
- Python 3 (Recommend to use [Anaconda](https://www.anaconda.com/download/#linux))
- [PyTorch >= 1.1](https://pytorch.org/)
- NVIDIA GPU + [CUDA](https://developer.nvidia.com/cuda-downloads)
- [Deformable Convolution v2](https://arxiv.org/abs/1811.11168), we adopt [CharlesShang's implementation](https://github.com/CharlesShang/DCNv2) in the submodule.
- Python packages: `pip install numpy opencv-python lmdb pyyaml pickle5 matplotlib seaborn`
## Get Started
### Installation
Install the required packages: `pip install -r requirements.txt`
First, make sure your machine has a GPU, which is required for the DCNv2 module.
1. Clone the Zooming Slow-Mo repository. We'll call the directory that you cloned Zooming Slow-Mo as ZOOMING_ROOT.
```Shell
git clone --recursive https://github.com/Mukosame/Zooming-Slow-Mo-CVPR-2020.git
```
2. Compile the DCNv2:
```Shell
cd $ZOOMING_ROOT/codes/models/modules/DCNv2
bash make.sh # build
python test.py # run examples and gradient check
```
Please make sure the test script finishes successfully without any errors before running the following experiments.
### Training
#### Part 1: Data Preparation
1. Download tExcerpt of 10,231 characters
Read on GitHub
Xiaoyu Xiang · Meta · United States
17
2
2
1
1
1
1
Would you bet a product on this? Bounded 0–100 and slow moving.
matched fp:16e8ff8b71c79c80, topic:super-resolution, desc:super resolution, readme:super resolution
matched fp:16e8ff8b71c79c80, topic:pytorch