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.
iSeeBetter: Spatio-Temporal Video Super Resolution using Recurrent-Generative Back-Projection Networks | Python3 | PyTorch | GANs | CNNs | ResNets | RNNs | Published in Springer Journal of Computational Visual Media, September 2020, Tsinghua University Press
| Date | Stars |
|---|---|
| 2026-07-24 | 382 |
| 2026-07-25 | 382 |
| 2026-07-28 | 382 |
| 2026-07-30 | 382 |
| 2026-08-06 | 382 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
# iSeeBetter: Spatio-Temporal Video Super Resolution using Recurrent-Generative Back-Projection Networks
<a href="https://link.springer.com/article/10.1007/s41095-020-0175-7"><p align=center><img src="https://github.com/amanchadha/iSeeBetter/blob/master/spr.jpg"/></p></a>
Project for Stanford CS230: Deep Learning. Published in **Springer Journal of Computational Visual Media, September 2020, Tsinghua University Press**.
This is the official PyTorch implementation of our paper.
```Python3 | PyTorch | GANs | CNNs | ResNets | RNNs```
---
### PDF: **[SpringerLink](https://link.springer.com/article/10.1007/s41095-020-0175-7)** | **[arXiv](https://arxiv.org/abs/2006.11161)** | **[amanchadha.com](https://amanchadha.com/research/ChadhaBrittoRoja_iSeeBetterCVM.pdf)**
### Misc: **<a href="https://www.youtube.com/watch?v=2HC0wdeQRiM">YouTube Video</a> | <a href="https://amanchadha.com/research/AmanChadha_CS230_Poster.pdf">Poster</a> | <a href="https://paperswithcode.com/paper/iseebetter-spatio-temporal-video-super">PapersWithCode</a> | <a href="https://www.researchgate.net/publication/342165676_iSeeBetter_Spatio-Temporal_Video_Super-Resolution_using_Recurrent_Generative_Back-Projection_Networks">ResearchGate</a> | <a href="https://www.mendeley.com/catalogue/3e9119ff-174b-3c07-9683-aafe8800af32/">Mendeley</a> | <a href="https://ui.adsabs.harvard.edu/abs/2020arXiv200611161C/abstract">NASA ADS</a> | <a href="https://www.semanticscholar.org/paper/iSeeBetter%3A-Spatio-temporal-video-super-resolution-Chadha/96848693030ba20518ebb12b3dd2c4d4e04ec886">SemanticScholar</a>**
---
We’re #1 on the Video Super Resolution leaderboard on [PapersWithCode](https://paperswithcode.com/sota/video-super-resolution-on-vid4-4x-upscaling)!
<a href="https://paperswithcode.com/sota/video-super-resolution-on-vid4-4x-upscaling"><p align=center><img src="https://github.com/amanchadha/iSeeBetter/blob/master/vid4.jpg" width="600px" height="400px"/></p></a>
---
## Citation
If you found our work interesting, please cite it as:
```
@article{Chadha2020iSeeBetter,
title={{i}{S}ee{B}etter: Spatio-Temporal Video Super-Resolution using Recurrent Generative Back-Projection Networks},
author={Chadha, Aman and Britto, John and Roja, Mani M.},
journal={Springer Journal of Computational Visual Media, September 2020, Tsinghua University Press},
volume={6},
number={3},
pages={307-317},
year={2020},
publisher={Springer}
}
```
```
A. Chadha, J. Britto and M. M. Roja. iSeeBetter: Spatio-Temporal Video Super-Resolution using Recurrent Generative Back-Projection Networks. Springer Journal of Computational Visual Media, Tsinghua University Press, 6(3):1–11, 2020.
```
## Required Packages
```
torch==1.3.0.post2
pytorch-ssim==0.1
numpy==1.16.4
scikit-image==0.15.0
tqdm==4.37.0
opencv-python==4.5.1.48
```
Step 0: To load the required Python modules:
```bash
pip3 install -r requirements.txt
```
Also needed is [Pyflow](https://github.com/pathak22/pyflow) which is a Python wrapper for [Ce Liu's C++ implementation](https://people.csail.mit.edu/celiu/OpticalFlow/) of Coarse2Fine Optical Flow.
Pyflow binaries that we used have been built for Ubuntu and macOS with Python 3.7 and are available in the repository.
If you need to rebuild Pyflow, (i) simply follow the instructions below or (ii) refer to the [Pyflow Git](https://github.com/pathak22/pyflow)
Step 1: Build Pyflow:
```bash
cd pyflow/
python setup.py build_ext -i # build pyflow
python demo.py # to make sure pyflow works
cp pyflow*.so ..
```
Step 2: Train or test iSeeBetter using the instructions in the relevant sections below.
## Elevator Pitch
Deep learning has taken the world by storm!
Amongst the plethora of fields that deep learning has impacted, super resolution (which by definition is upscaling a low-res sample to a high-res sample) is one of them.
So why did I chose this topic? IExcerpt of 12,321 characters
Read on GitHubWould you bet a product on this? Bounded 0–100 and slow moving.
matched fp:8599fe9f78d0be7e, topic:super-resolution, topic:gan, readme:upscaling