Skip to content

Supervised Raw Video Denoising with a Benchmark Dataset on Dynamic Scenes. CVPR 2020

Notifications You must be signed in to change notification settings

cao-cong/RViDeNet

Repository files navigation

Supervised Raw Video Denoising with a Benchmark Dataset on Dynamic Scenes (RViDeNet)

This repository contains official implementation of Supervised Raw Video Denoising with a Benchmark Dataset on Dynamic Scenes in CVPR 2020, by Huanjing Yue, Cong Cao, Lei Liao, Ronghe Chu, and Jingyu Yang.

Paper

http://openaccess.thecvf.com/content_CVPR_2020/papers/Yue_Supervised_Raw_Video_Denoising_With_a_Benchmark_Dataset_on_Dynamic_CVPR_2020_paper.pdf
http://openaccess.thecvf.com/content_CVPR_2020/supplemental/Yue_Supervised_Raw_Video_CVPR_2020_supplemental.pdf

Demo Video

https://youtu.be/5za3d81Eiqk

Dataset

Captured Raw Video Denoising Dataset (CRVD Dataset)

You can download our dataset from Google Drive or MEGA or Baidu Netdisk (key: cdux). We also provide original averaged frame (without applying BM3D) in folder "indoor_raw_noisy", named like "frameXX_clean.tiff". The Bayer pattern of raw data is GBRG, the black level is 240, the white level is 2^12-1. You can apply your ISP to raw data to generate sRGB video denoising data.

Copyright

The CRVD dataset is available for the academic purpose only. Any researcher who uses the CRVD dataset should obey the licence as below:

All of the CRVD Dataset (data and software) are copyright by Intelligent Imaging and Reconstruction Laboratory, Tianjin University and published under the Creative Commons Attribution-NonCommercial-ShareAlike 4.0 License. This means that you must attribute the work in the manner specified by the authors, you may not use this work for commercial purposes and if you alter, transform, or build upon this work, you may distribute the resulting work only under the same license.

This dataset is for non-commercial use only. However, if you find yourself or your personal belongings in the data, please contact us, and we will immediately remove the respective images from our servers.

Code

Dependencies and Installation

  • Ubuntu
  • Python 3.5
  • NVIDIA GPU + CUDA 9.0 + CuDNN 7
  • Pytorch 1.0
  • Tensorflow 1.5 gpu (only to synthesize raw data)
  • Deformable Convolution
    cd ./modules/DCNv2
    bash make.sh
    
  • Criss-Cross Attention
    cd ./modules/cc_attention
    python setup.py develop
    

Prepare Data

  • Download SID dataset. Select raw clean images to generate raw noisy images to train PreDenoising module, select raw clean images and corresponding sRGB clean images to train ISP module.
  • Prepare synthesized raw video denoising dataset (SRVD dataset) to pretrain RViDeNet. Please download MOT Challenge dataset and select four videos (02, 09, 10, 11) from train set. To convert sRGB clean videos to raw clean videos, run:
    python sRGB_to_raw.py
    
  • To generate raw noisy videos from raw clean videos, run:
    python synthesize_noise.py
    
  • Download captured raw video denoising dataset (CRVD dataset) to finetune RViDeNet.

Test

  • Please download trained model from Google Drive or Baidu Netdisk (key: xssc).
  • Test pretrained RViDeNet on indoor test set (scene 7, 8, 9, 10, 11) of CRVD dataset.
    python test_indoor.py --model pretrain --gpu_id 0  --output_dir ./results/pretrain/ --vis_data True
    
  • Test finetuned RViDeNet on indoor test set (scene 7, 8, 9, 10, 11) of CRVD dataset.
    python test_indoor.py --model finetune --gpu_id 0  --output_dir ./results/finetune/ --vis_data True
    

Train

  • Train the ISP module. Please run 'convert_to_tiff.py' and 'rename_gt_png.py' to process SID Sony dataset, then run:
    python train_isp.py --gpu_id 0  --num_epochs 770 --patch_size 512
    
  • Train the PreDenoising module.
    python train_predenoising.py --gpu_id 0  --num_epochs 700 --patch_size 128
    
  • Pretrain RViDeNet on SRVD dataset.
    python train_pretrain.py --gpu_id 0  --num_epochs 33 --patch_size 128 --batch_size 1
    
  • Finetune RViDeNet on CRVD dataset (scene 1-6).
    python train_finetune.py --gpu_id 0  --num_epochs 70 --patch_size 128 --batch_size 1
    

Citation

If you find our dataset or code helpful in your research or work, please cite our paper:

@inproceedings{yue2020supervised,
  title={Supervised Raw Video Denoising with a Benchmark Dataset on Dynamic Scenes},
  author={Yue, Huanjing and Cao, Cong and Liao, Lei and Chu, Ronghe and Yang, Jingyu},
  booktitle={IEEE Conference on Computer Vision and Pattern Recognition},
  year={2020}
}

Acknowledgement

Our work and implementations are inspired by following projects:
[Unprocessing] (https://github.com/google-research/google-research/tree/master/unprocessing)
[EDVR] (https://github.com/xinntao/EDVR)
[SID] (https://github.com/cchen156/Learning-to-See-in-the-Dark)
[DANet] (https://github.com/junfu1115/DANet)
[CCNet] (https://github.com/speedinghzl/CCNet)

About

Supervised Raw Video Denoising with a Benchmark Dataset on Dynamic Scenes. CVPR 2020

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published