Top AI Repos β 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.
"Retinexformer: One-stage Retinex-based Transformer for Low-light Image Enhancement" (ICCV 2023 Top-10 Cited π) & (NTIRE 2024 Runner-Up π) & (NTIRE 2025 Winner π) & (NTIRE 2026 Winner π)
| Date | Stars |
|---|---|
| 2026-07-24 | 1501 |
| 2026-07-25 | 1501 |
| 2026-07-28 | 1501 |
| 2026-07-30 | 1501 |
| 2026-08-06 | 1501 |
Today
β stars today
This week
β stars this week
This month
β stars this month
Momentum
0.0
growth rate 0.00%/day
<div align="center"> <p align="center"> <img src="figure/logo.png" width="200px"> </p> [](https://arxiv.org/abs/2303.06705) [](https://codalab.lisn.upsaclay.fr/competitions/17640#results) [](https://zhuanlan.zhihu.com/p/657927878) </div> ### Introduction This is a baseline and toolbox for low-light image enhancement. This repo **supports over 15 benchmarks** and extremely high-resolution (up to 4000x6000) low-light enhancement. Our method Retinexformer **won the second place** in the [NTIRE 2024 Challenge on Low Light Enhancement](https://codalab.lisn.upsaclay.fr/competitions/17640) π. Later works based on our Retinexformer won the [NTIRE 2025 Low-light Image Enhancement Challenge](https://codalab.lisn.upsaclay.fr/competitions/21636) π and [NTIRE 2026 Efficient Low-light Image Enhancement Challenge](https://www.codabench.org/competitions/13382/) π. If you find this repo useful, please give it a star β and consider citing our paper. Thank you. ### Awards <img src="./figure/ntire.png" height=240> <img src="./figure/NTIRE_2024_award.png" height=240> ### News - **2026.05.23 :** The winner solution of [NTIRE 2026 Efficient Low-light Image Enhancement Challenge](https://www.codabench.org/competitions/13382/) is based on our Retinexformer. Congraduation to them. Feel free to check the [challenge report](https://arxiv.org/abs/2605.02212) π - **2025.06.05 :** The winner solution of [NTIRE 2025 Low-light Image Enhancement Challenge](https://codalab.lisn.upsaclay.fr/competitions/21636) is based on our Retinexformer. Congraduation to them. Feel free to check the [challenge report](https://openaccess.thecvf.com/content/CVPR2025W/NTIRE/papers/Liu_NTIRE_2025_Challenge_on_Low_Light_Image_Enhancement_Methods_and_CVPRW_2025_paper.pdf) and their [challenge paper](https://openaccess.thecvf.com/content/CVPR2025W/NTIRE/papers/Shi_FusionNet_Multi-model_Linear_Fusion_Framework_for_Low-light_Image_Enhancement_CVPRW_2025_paper.pdf) π - **2025.02.10 :** [NTIRE 2025 Low-light Image Enhancement Challenge](https://codalab.lisn.upsaclay.fr/competitions/21636) has started. Welcome to use our Retinexformer and MST to participate in this challenge. π - **2024.09.15 :** An enhanced version of Retinexformer (ECCV 2024) has been released at [this repo](https://github.com/redrock303/ADF-LLIE). Feel free to check and use it. π€ - **2024.08.07 :** We share the code that can draw our teaser figure (the bar comparison) [here](https://github.com/caiyuanhao1998/draw_script/tree/master/bar). Feel free to use it in your research :smile: - **2024.07.03 :** We share more results of compared baseline methods to help your research. Feel free to download them from [Google Drive](https://drive.google.com/drive/folders/1P75bv6jBp8UxcLDhqMACvIQXck2sS9da?usp=sharing) or [Baidu Disk](https://pan.baidu.com/s/1ksGGV6nMyVVE6OqGuyO8_w?pwd=cyh2) :smile: - **2024.07.01 :** An enhanced version of Retinexformer has been accepted by ECCV 2024. Code will be released. Stay tuned. π - **2024.05.12 :** [RetinexMamba](https://github.com/YhuoyuH/RetinexMamba) based on our Retinexformer framework and this repo has been released. The first Mamba work on low-light enhancement. Thanks to the efforts of the authors. - **2024.03.22 :** We release `distributed data parallel (DDP)` and `mix-precision` training strategies to help you train larger models. We release `self-ensemble` testing strategy to help you derive better results. In addition, we also release an adaptive `split-and-test` testing strategy for high-resolution up to 4000x6000 low-light image enhancement. Feel free to use them. π - **2024.03.21 :** Our methods [Retinexformer](https://github.com/caiyuanhao1998/Retinexformer) and [MST++](https://github.com/caiyuanhao1998/MST-plus-plus) (NTIRE 2022 Spectral Reconstruction Challenge Winner) ra
Excerpt of 28,165 characters
Read on GitHub
Yuanhao Cai Β· Johns Hopkins University <- Tsinghua Β· United States
140
8
Would you bet a product on this? Bounded 0β100 and slow moving.
matched fp:6440d86996196d59, topic:transformer
matched fp:6440d86996196d59, topic:object-detection