Density-aware Single Image De-raining using a Multi-stream Dense Network (CVPR 2018)

Overview

DID-MDN

Density-aware Single Image De-raining using a Multi-stream Dense Network

He Zhang, Vishal M. Patel

[Paper Link] (CVPR'18)

We present a novel density-aware multi-stream densely connected convolutional neural network-based algorithm, called DID-MDN, for joint rain density estimation and de-raining. The proposed method enables the network itself to automatically determine the rain-density information and then efficiently remove the corresponding rain-streaks guided by the estimated rain-density label. To better characterize rain-streaks with dif- ferent scales and shapes, a multi-stream densely connected de-raining network is proposed which efficiently leverages features from different scales. Furthermore, a new dataset containing images with rain-density labels is created and used to train the proposed density-aware network.

@inproceedings{derain_zhang_2018,		
  title={Density-aware Single Image De-raining using a Multi-stream Dense Network},
  author={Zhang, He and Patel, Vishal M},
  booktitle={CVPR},
  year={2018}
} 

Prerequisites:

  1. Linux
  2. Python 2 or 3
  3. CPU or NVIDIA GPU + CUDA CuDNN (CUDA 8.0)

Installation:

  1. Install PyTorch and dependencies from http://pytorch.org (Ubuntu+Python2.7) (conda install pytorch torchvision -c pytorch)

  2. Install Torch vision from the source. (git clone https://github.com/pytorch/vision cd vision python setup.py install)

  3. Install python package: numpy, scipy, PIL, pdb

Demo using pre-trained model

python test.py --dataroot ./facades/github --valDataroot ./facades/github --netG ./pre_trained/netG_epoch_9.pth   

Pre-trained model can be downloaded at (put it in the folder 'pre_trained'): https://drive.google.com/drive/folders/1VRUkemynOwWH70bX9FXL4KMWa4s_PSg2?usp=sharing

Pre-trained density-aware model can be downloaded at (Put it in the folder 'classification'): https://drive.google.com/drive/folders/1-G86JTvv7o1iTyfB2YZAQTEHDtSlEUKk?usp=sharing

Pre-trained residule-aware model can be downloaded at (Put it in the folder 'residual_heavy'): https://drive.google.com/drive/folders/1bomrCJ66QVnh-WduLuGQhBC-aSWJxPmI?usp=sharing

Training (Density-aware Deraining network using GT label)

python derain_train_2018.py  --dataroot ./facades/DID-MDN-training/Rain_Medium/train2018new  --valDataroot ./facades/github --exp ./check --netG ./pre_trained/netG_epoch_9.pth.
Make sure you download the training sample and put in the right folder

Density-estimation Training (rain-density classifier)

python train_rain_class.py  --dataroot ./facades/DID-MDN-training/Rain_Medium/train2018new  --exp ./check_class	

Testing

python demo.py --dataroot ./your_dataroot --valDataroot ./your_dataroot --netG ./pre_trained/netG_epoch_9.pth   

Reproduce

To reproduce the quantitative results shown in the paper, please save both generated and target using python demo.py into the .png format and then test using offline tool such as the PNSR and SSIM measurement in Python or Matlab. In addition, please use netG.train() for testing since the batch for training is 1.

Dataset

Training (heavy, medium, light) and testing (TestA and Test B) data can be downloaded at the following link: https://drive.google.com/file/d/1cMXWICiblTsRl1zjN8FizF5hXOpVOJz4/view?usp=sharing

License

Code is under MIT license.

Acknowledgments

Great thanks for the insight discussion with Vishwanath Sindagi and help from Hang Zhang

Owner
He Zhang
Research Sc[email protected], Phd in Computer Vision, Deep Learning
He Zhang
Technical experimentations to beat the stock market using deep learning :chart_with_upwards_trend:

DeepStock Technical experimentations to beat the stock market using deep learning. Experimentations Deep Learning Stock Prediction with Daily News Hea

Keon 449 Dec 29, 2022
TransVTSpotter: End-to-end Video Text Spotter with Transformer

TransVTSpotter: End-to-end Video Text Spotter with Transformer Introduction A Multilingual, Open World Video Text Dataset and End-to-end Video Text Sp

weijiawu 66 Dec 26, 2022
My coursework for Machine Learning (2021 Spring) at National Taiwan University (NTU)

Machine Learning 2021 Machine Learning (NTU EE 5184, Spring 2021) Instructor: Hung-yi Lee Course Website : (https://speech.ee.ntu.edu.tw/~hylee/ml/202

100 Dec 26, 2022
A collection of IPython notebooks covering various topics.

ipython-notebooks This repo contains various IPython notebooks I've created to experiment with libraries and work through exercises, and explore subje

John Wittenauer 2.6k Jan 01, 2023
[ICCV2021] 3DVG-Transformer: Relation Modeling for Visual Grounding on Point Clouds

3DVG-Transformer This repository is for the ICCV 2021 paper "3DVG-Transformer: Relation Modeling for Visual Grounding on Point Clouds" Our method "3DV

22 Dec 11, 2022
Differentiable scientific computing library

xitorch: differentiable scientific computing library xitorch is a PyTorch-based library of differentiable functions and functionals that can be widely

98 Dec 26, 2022
Create and implement a deep learning library from scratch.

In this project, we create and implement a deep learning library from scratch. Table of Contents Deep Leaning Library Table of Contents About The Proj

Rishabh Bali 22 Aug 23, 2022
GAN example for Keras. Cuz MNIST is too small and there should be something more realistic.

Keras-GAN-Animeface-Character GAN example for Keras. Cuz MNIST is too small and there should an example on something more realistic. Some results Trai

160 Sep 20, 2022
implementation of the paper "MarginGAN: Adversarial Training in Semi-Supervised Learning"

MarginGAN This repository is the implementation of the paper "MarginGAN: Adversarial Training in Semi-Supervised Learning". 1."preliminary" is the imp

Van 7 Dec 23, 2022
Unrestricted Facial Geometry Reconstruction Using Image-to-Image Translation

Unrestricted Facial Geometry Reconstruction Using Image-to-Image Translation [Arxiv] [Video] Evaluation code for Unrestricted Facial Geometry Reconstr

Matan Sela 242 Dec 30, 2022
A collection of easy-to-use, ready-to-use, interesting deep neural network models

Interesting and reproducible research works should be conserved. This repository wraps a collection of deep neural network models into a simple and un

Aria Ghora Prabono 16 Jun 16, 2022
TorchIO is a Medical image preprocessing and augmentation toolkit for deep learning. Part of the PyTorch Ecosystem.

Medical image preprocessing and augmentation toolkit for deep learning. Part of the PyTorch Ecosystem.

Fernando Pérez-García 1.6k Jan 06, 2023
OverFeat is a Convolutional Network-based image classifier and feature extractor.

OverFeat OverFeat is a Convolutional Network-based image classifier and feature extractor. OverFeat was trained on the ImageNet dataset and participat

593 Dec 08, 2022
Confident Semantic Ranking Loss for Part Parsing

Confident Semantic Ranking Loss for Part Parsing

Jiachen Xu 5 Oct 22, 2022
Post-Training Quantization for Vision transformers.

PTQ4ViT Post-Training Quantization Framework for Vision Transformers. We use the twin uniform quantization method to reduce the quantization error on

Zhihang Yuan 61 Dec 28, 2022
ONNX-PackNet-SfM: Python scripts for performing monocular depth estimation using the PackNet-SfM model in ONNX

Python scripts for performing monocular depth estimation using the PackNet-SfM model in ONNX

Ibai Gorordo 14 Dec 09, 2022
Project of 'TBEFN: A Two-branch Exposure-fusion Network for Low-light Image Enhancement '

TBEFN: A Two-branch Exposure-fusion Network for Low-light Image Enhancement Codes for TMM20 paper "TBEFN: A Two-branch Exposure-fusion Network for Low

KUN LU 31 Nov 06, 2022
Unofficial pytorch-lightning implement of Mip-NeRF

mipnerf_pl Unofficial pytorch-lightning implement of Mip-NeRF, Here are some results generated by this repository (pre-trained models are provided bel

Jianxin Huang 159 Dec 23, 2022
Oscar and VinVL

Oscar: Object-Semantics Aligned Pre-training for Vision-and-Language Tasks VinVL: Revisiting Visual Representations in Vision-Language Models Updates

Microsoft 938 Dec 26, 2022
DirectVoxGO reconstructs a scene representation from a set of calibrated images capturing the scene.

DirectVoxGO reconstructs a scene representation from a set of calibrated images capturing the scene. We achieve NeRF-comparable novel-view synthesis quality with super-fast convergence.

sunset 709 Dec 31, 2022