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.
[ICCP'22] Rethinking Learning-based Demosaicing, Denoising, and Super-Resolution Pipeline
| Date | Stars |
|---|---|
| 2026-07-24 | 303 |
| 2026-07-25 | 303 |
| 2026-07-28 | 303 |
| 2026-07-30 | 303 |
| 2026-08-06 | 303 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
# TENet <a href="https://arxiv.org/abs/1905.02538" target="_blank">[ArXiv]</a> <a href="http://guochengqian.github.io/project/pixelshift200">[pixelshift200]</a>
### Rethinking Learning-based Demosaicing, Denoising, and Super-Resolution Pipeline
By [Guocheng Qian*](https://guochengqian.github.io/), [Yuanhao Wang*](https://github.com/yuanhaowang1213), [Jinjin Gu](http://www.jasongt.com/), Chao Dong, Wolfgang Heidrich, Bernard Ghanem, [Jimmy S. Ren](http://www.jimmyren.com/)
The original name of this project is: "Trinity of Pixel Enhancement: a Joint Solution for Demosaicking, Denoising and Super-Resolution"
## TENet
We insert the proposed pipeline DN -> SR -> DM into an end-to-end network constructed by RRDB for the joint DN, DM and SR. We leverage the detachable branch to provide the middle stage supervision.
<p align="center">
<img height="300" src="misc/Network.png">
</p>
## PixelShift200 dataset
We employ advanced pixel shift technology to perform a full color sampling of the image.
Pixel shift technology takes four samples of the same image, and physically controls the camera sensor to move one pixel horizontally or vertically at each sampling to capture all color information at each pixel.
The pixel shift technology ensures that the sampled images follow the distribution of natural images sampled by the camera, and the full information of the color is completely obtained.
In this way, the collected images are artifacts-free, which leads to better training results for demosaicing related tasks.
<p align="center">
<img height="200" src="misc/PixelShift.png">
</p>
Download PixelShift200 and the original RAW files from [pxielshift200 website](http://guochengqian.github.io/project/pixelshift200) for using this [Google Drive Link](https://drive.google.com/drive/folders/1S1mt9D8IlpSAVm7RTjLheh1hTaltsV_f?usp=share_link)
### Environment installation
Clone this github repo and install the environment by:
```bash
git clone --recurse-submodules https://github.com/guochengqian/TENet
cd TENet
source install.sh
source .venv/bin/activate
```
The default `install.sh` targets modern NVIDIA GPUs, **including Blackwell (RTX 50-series / RTX 5090, sm_120)**, using a uv + Python 3.12 environment with PyTorch ≥2.7 built for CUDA 12.8 (`cu128`). TENet has no custom CUDA ops, so no compilation is needed. The legacy CUDA 11.1 / PyTorch 1.10 conda recipe is kept (commented) at the bottom of `install.sh` for older GPUs.
### Pip helper package
Resource metadata and a small info CLI are available on PyPI:
```bash
pip install tenet_official
tenet-info # paper, code, and PixelShift200 dataset links
tenet-info --models # list model variants
```
Training/evaluation still uses this source checkout; `tenet_official` only ships metadata/resource pointers.
### Data preparation
1. synthetic data preparation [Optional]
Processing synthetic dataset if you are interested in synthetic benchmark.
1. Download ([DIV2K](https://drive.google.com/file/d/1vXPPr2hVaMewz2JA1lFfI5uHB4ENwRXQ/view?usp=sharing)) dataset
2. `mkdir data && cd data`
3. Link DIV2K data into ./data/DIV2K, e.g. `ln -s /data/lowlevel/DIV2K ./`
4. Crop DIV2K
```bash
cd ../datasets
python crop_imgs.py # crop train images
python crop_imgs.py --src_dir ../data/DIV2K/DIV2K_val5_HR --save_dir ../data/DIV2K/DIV2K_val5_HR_sub # crop val5 images
```
2. PixelShift200 data preparation
Processing PixelShift200 dataset if you are interested in PixelShift200 benchmark.
1. Download [Pixelshift200](http://guochengqian.com/pixelshift200). They are .mat format, having 4 channels (R, Gr, Gb, B). Unzip the .zip file and put all folders inside into one folder called pixelshift200. For example, put here `/data/lowlevel/pixelshift200`.
2. `cd TENet && mkdir data && cd data`
3. Link PixelShift200 data into ./data/pixelshift200, e.g. `ln -s /data/lowlevel/pixelshift200 pixelshift200`
4. Crop images inExcerpt of 8,068 characters
Read on GitHubWould you bet a product on this? Bounded 0–100 and slow moving.
matched fp:77c4303ae6c75e33, topic:super-resolution, desc:super resolution, readme:super resolution
matched fp:77c4303ae6c75e33, topic:pytorch