cchen156 /Learning-to-See-in-the-Dark
Learning to See in the Dark. CVPR 2018
★ 5,567⑂ 835👁 169⑃ 17● 111▤ 0
+0
日增长
5,567
stars
835
forks
169
watchers
17
prs
111
issues
0
releases
README
Learning-to-See-in-the-Dark
This is a Tensorflow implementation of Learning to See in the Dark in CVPR 2018, by Chen Chen, Qifeng Chen, Jia Xu, and Vladlen Koltun.
Project Website
Paper
!teaser
This code includes the default model for training and testing on the See-in-the-Dark (SID) dataset.
Demo Video
https://youtu.be/qWKUFK7MWvg
Setup
Requirement
Required python (version 2.7) libraries: Tensorflow (=1.1) + Scipy + Numpy + Rawpy.
Tested in Ubuntu + Intel i7 CPU + Nvidia Titan X (Pascal) with Cuda (=8.0) and CuDNN (=5.0). CPU mode should also work with minor changes but not tested.
Dataset
Update Sep, 2025: We got signicant bills from Google storage. Please download the data manually and save a copy locally. Avoid re-downloading the data per experiment run. The download script is removed. Thank you!
Update Aug, 2018: We found some misalignment with the ground-truth for image 10034, 10045, 10172. Please remove those images for quantitative results, but they still can be used for qualitative evaluations.
You can download it directly from Google drive for the Sony (25 GB) and Fuji (52 GB) sets.
There is download limit by Google drive in a fixed period of time. If you cannot download because of this, try these links: Sony (25 GB) and Fuji (52 GB).
New: we provide file parts in Baidu Drive now. After you download all the parts, you can combine them together by running: "cat SonyPart Sony.zip" and "cat FujiPart Fuji.zip".
The file lists are provided. In each row, there are a short-exposed image path, the corresponding long-exposed image path, camera ISO and F number. Note that multiple short-exposed images may correspond to the same long-exposed image.
The file name contains the image information. For example, in "10019_00_0.033s.RAF", the first digit "1" means it is from the test set ("0" for training set and "2" for validation set); "0019" is the image ID; the following "00" is the number in the sequence/burst; "0.033s" is the exposure time 1/30 seconds.
Testing
1. Clone this repository.
2. Download the pretrained models by running
Shell
python download_models.py
3. Run "python test_Sony.py". This will generate results on the Sony test set.
4. Run "python test_Fuji.py". This will generate results on the Fuji test set.
By default, the code takes the data in the "./dataset/Sony/" folder and "./dataset/Fuji/". If you save the dataset in other folders, please change the "input_dir" and "gt_dir" at the beginning of the code.
Training new models
1. To train the Sony model, run "python train_Sony.py". The result and model will be save in "result_Sony" folder by default.
2. To train the Fuji model, run "python train_Fuji.py". The result and model will be save in "result_Fuji" folder by default.
By default, the code takes the data in the "./dataset/Sony/" folder and "./dataset/Fuji/". If you save the dataset in other folders, please change the "input_dir" and "gt_dir" at the beginning of the code.
Loading the raTop issues
#75how to test the model on my own dataset29 comments · 2019-04-03#94Will the Sony model work for dual camera iPhone?15 comments · 2019-09-29#73Output is all black15 comments · 2019-03-18#45misalignment problem in the dataset13 comments · 2018-08-07#34error in test_Sony.py12 comments · 2018-07-10#14comparison between output of SID(see in the dark) and photoshop11 comments · 2018-05-22#71Output blurry and black and white9 comments · 2019-02-22#23Questions regarding to the PSNR/SSIM results9 comments · 2018-06-13