Source code for CVPR2022 paper "Abandoning the Bayer-Filter to See in the Dark"

Overview

Abandoning the Bayer-Filter to See in the Dark (CVPR 2022)

Paper: https://arxiv.org/abs/2203.04042 (Arxiv version)

This code includes the training and testing procedures of our network on our Mono-colored raw Paired (MCR) dataset and SID dataset's Sony part.

Abstract: Low-light image enhancement - a pervasive but challenging problem, plays a central role in enhancing the visibility of an image captured in a poor illumination environment. Due to the fact that not all photons can pass the Bayer-Filter on the sensor of the color camera, in this work, we first present a De-Bayer-Filter simulator based on deep neural networks to generate a monochrome raw image from the colored raw image. Next, a fully convolutional network is proposed to achieve the low-light image enhancement by fusing colored raw data with synthesized monochrome raw data. Channel-wise attention is also introduced to the fusion process to establish a complementary interaction between features from colored and monochrome raw images. To train the convolutional networks, we propose a dataset with monochrome and color raw pairs named Mono-Colored Raw paired dataset (MCR) collected by using a monochrome camera without Bayer-Filter and a color camera with Bayer-Filter. The proposed pipeline take advantages of the fusion of the virtual monochrome and the color raw images and our extensive experiments indicate that significant improvement can be achieved by leveraging raw sensor data and data-driven learning.

pipeline

Video demos:

videos

Requirments

This is the Pytorch implementation of our work. The next requirments and some other frequently-used Library will be needed.

  1. Python >= 3.7
  2. Pytorch >= 1.7.1
  3. scikit-image 0.18.1
  4. imageio 2.9.0
  5. rawpy 0.17.0

Dataset

dataset

We propose the MCR [Google Drive, Baidu Netdisk (Extraction code: 22cv)], a dataset of colored raw and monochrome raw image pairs, captured with the same exposure setting. Each image has a resolution of 1280×1024.

The zip file contain 3 parts:

  • Mono_Colored_RAW_Paired_DATASET
    • RGB_GT (498 images)
    • Mono_GT (498 images)
    • Color_RAW_Input (498 × 8 images)

Totally 498 different scenes, each scene has 1 corresponding RGB and Monochrome ground truth and 8 different exposure color Raw inputs.

We assemble the color camera and the monochrome camera up and down, setting the same exposure times and gain in the same scene.

And we choose the monochrome GT and RGB GT under the longest exposure time.

The file name contains the image information. Take the image name:"C00001_48mp_0x8_0x1fff.tif" as an example.

"C" means it is color raw image;

"00001" is the image number;

"48mp" is the master clock frequency 48 MHz;

"0x8" is the hex number of global gain;

"0x1fff" indicate the shutter width of the camera which can calculate the exposure time.

For visual convenience, we convert '.raw' files to '.tif' files which have the same 'RGGB' Bayer-filter pattern as the raw files.

The relationship between shutter width and the exposure time is shown in the table below.

teaser

The first 2 rows represent the exposure time settings in the indoor scenes which image number is between 1 and 499, the last 2 rows represent outdoor scenes' exposure time settings.

Alignment

We propose our alignment code for color and monochrome images taken by 2 cameras under the same scene.

Alignment/raw folder contain samples of color and monochrome raw images in one scene.

Firstly,in convert_RAW.py, we reshape the flatten '.raw' files into '1280×1024' and save as '.tif' files, and then we use the 'exiftool.exe' to add the head info 'pbpx_exft_args.txt' and save the images as '.dng' and '.jpg' files.

Secondly, in alignment.py, we choose two '.jpg' images from color and monochrome, and use opencv to calculate the homograph to do the alignment for monochrome images.

Training & Testing

For fully loading our dataset, 36G RAM are needed.

The 'random_path_list' contain the split train&test path lists in our dataset.

We split 3984 pairs of our dataset into train set: 3600 pairs and test set: 384 pairs

We train and test our MCR dataset with train.py and test.py, and we also train our network on SID dataset's Sony part with train_on_SID.py and test_on_SID.py.

The pre-trained models on both datasets can be found at MCR_pretrained_model and SID_pretrained_model

Citation

If you find this project useful in your research, please consider citing:

@inproceedings{Dong2022Abandoning,
	title={Abandoning the Bayer-Filter to See in the Dark},
	author={Dong, Xingbo and Xu, Wanyan and Miao, Zhihui and Ma, Lan and Zhang, Chao and Yang, Jiewen and Jin, Zhe and Teoh, Andrew Beng Jin and Shen, Jiajun},
	booktitle={Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
	year={2022}
}

License

Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.

Variational Attention: Propagating Domain-Specific Knowledge for Multi-Domain Learning in Crowd Counting (ICCV, 2021)

DKPNet ICCV 2021 Variational Attention: Propagating Domain-Specific Knowledge for Multi-Domain Learning in Crowd Counting Baseline of DKPNet is availa

19 Oct 14, 2022
Code, Models and Datasets for OpenViDial Dataset

OpenViDial This repo contains downloading instructions for the OpenViDial dataset in 《OpenViDial: A Large-Scale, Open-Domain Dialogue Dataset with Vis

119 Dec 08, 2022
BLEND: A Fast, Memory-Efficient, and Accurate Mechanism to Find Fuzzy Seed Matches

BLEND is a mechanism that can efficiently find fuzzy seed matches between sequences to significantly improve the performance and accuracy while reducing the memory space usage of two important applic

SAFARI Research Group at ETH Zurich and Carnegie Mellon University 19 Dec 26, 2022
Official PyTorch implementation for FastDPM, a fast sampling algorithm for diffusion probabilistic models

Official PyTorch implementation for "On Fast Sampling of Diffusion Probabilistic Models". FastDPM generation on CIFAR-10, CelebA, and LSUN datasets. S

Zhifeng Kong 68 Dec 26, 2022
One implementation of the paper "DMRST: A Joint Framework for Document-Level Multilingual RST Discourse Segmentation and Parsing".

Introduction One implementation of the paper "DMRST: A Joint Framework for Document-Level Multilingual RST Discourse Segmentation and Parsing". Users

seq-to-mind 18 Dec 11, 2022
Set of methods to ensemble boxes from different object detection models, including implementation of "Weighted boxes fusion (WBF)" method.

Set of methods to ensemble boxes from different object detection models, including implementation of "Weighted boxes fusion (WBF)" method.

1.4k Jan 05, 2023
Alfred-Restore-Iterm-Arrangement - An Alfred workflow to restore iTerm2 window Arrangements

Alfred-Restore-Iterm-Arrangement This alfred workflow will list avaliable iTerm2

7 May 10, 2022
Agile SVG maker for python

Agile SVG Maker Need to draw hundreds of frames for a GIF? Need to change the style of all pictures in a PPT? Need to draw similar images with differe

SemiWaker 4 Sep 25, 2022
Predicts an answer in yes or no.

Oui-ou-non-prediction Predicts an answer in 'yes' or 'no'. It is based on the game 'effeuiller la marguerite' in which the person plucks flower petals

Ananya Gupta 1 Jan 15, 2022
Creative Applications of Deep Learning w/ Tensorflow

Creative Applications of Deep Learning w/ Tensorflow This repository contains lecture transcripts and homework assignments as Jupyter Notebooks for th

Parag K Mital 1.5k Dec 30, 2022
TorchX: A PyTorch Extension Library for More Efficient Deep Learning

TorchX TorchX: A PyTorch Extension Library for More Efficient Deep Learning. @misc{torchx, author = {Ansheng You and Changxu Wang}, title = {T

Donny You 8 May 28, 2022
A chemical analysis of lipophilicities & molecule drawings including ML

A chemical analysis of lipophilicity & molecule drawings including a bit of ML analysis. This is a simple project that includes two Jupyter files (one

Aurimas A. Nausėdas 7 Nov 22, 2022
PyTorch implementation for "Sharpness-aware Quantization for Deep Neural Networks".

Sharpness-aware Quantization for Deep Neural Networks Recent Update 2021.11.23: We release the source code of SAQ. Setup the environments Clone the re

Zhuang AI Group 30 Dec 19, 2022
Simple cross-platform application for DaVinci surgical video frame annotation

About DaVid is a simple cross-platform GUI for annotating robotic and endoscopic surgical actions for use in deep-learning research. Features Simple a

Cyril Zakka 4 Oct 09, 2021
Example of semantic segmentation in Keras

keras-semantic-segmentation-example Example of semantic segmentation in Keras Single class example: Generated data: random ellipse with random color o

53 Mar 23, 2022
This is the official Pytorch implementation of the paper "Diverse Motion Stylization for Multiple Style Domains via Spatial-Temporal Graph-Based Generative Model"

Diverse Motion Stylization (Official) This is the official Pytorch implementation of this paper. Diverse Motion Stylization for Multiple Style Domains

Soomin Park 28 Dec 16, 2022
meProp: Sparsified Back Propagation for Accelerated Deep Learning

meProp The codes were used for the paper meProp: Sparsified Back Propagation for Accelerated Deep Learning with Reduced Overfitting (ICML 2017) [pdf]

LancoPKU 107 Nov 18, 2022
Simple, efficient and flexible vision toolbox for mxnet framework.

MXbox: Simple, efficient and flexible vision toolbox for mxnet framework. MXbox is a toolbox aiming to provide a general and simple interface for visi

Ligeng Zhu 31 Oct 19, 2019
Pytorch Implementation for (STANet+ and STANet)

Pytorch Implementation for (STANet+ and STANet) V2-Weakly Supervised Visual-Auditory Saliency Detection with Multigranularity Perception (arxiv), pdf:

GuotaoWang 14 Nov 29, 2022
DGL-TreeSearch and the Gurobi-MWIS interface

Independent Set Benchmarking Suite This repository contains the code for our maximum independent set benchmarking suite as well as our implementations

Maximilian Böther 19 Nov 22, 2022