GitPlanet

Cheap and reliable Node.js hosting starts at $3/month, and $1/month static HTML hosting

Created with love in Canada, visit hostnodejs.com today

Feel like to post an Ad? Learn Details
All Projects → m-tassano → Dvdnet

m-tassano / Dvdnet

Licence: gpl-3.0
DVDnet: A Simple and Fast Network for Deep Video Denoising

Programming Languages

python
139335 projects - #7 most used programming language
python3
1442 projects

Labels

deep-learningpytorchvideocnn

Projects that are alternatives of or similar to Dvdnet

Dl Colab Notebooks
Try out deep learning models online on Google Colab
Stars: ✭ 969 (+1961.7%)
Mutual labels:  cnn
Keras basic
keras를 이용한 딥러닝 기초 학습
Stars: ✭ 39 (-17.02%)
Mutual labels:  cnn
Mirror
Matchable Image Retrieval by Learning from Surface Reconstruction
Stars: ✭ 44 (-6.38%)
Mutual labels:  cnn
Covidaid
COVID-19 Detection Using Chest X-Ray
Stars: ✭ 35 (-25.53%)
Mutual labels:  cnn
Newsapi
News API without any API KEY
Stars: ✭ 39 (-17.02%)
Mutual labels:  cnn
Monodepth360
Master's project implementing depth estimation for spherical images using unsupervised learning with CNNs.
Stars: ✭ 41 (-12.77%)
Mutual labels:  cnn
Gaze Estimation
A deep learning based gaze estimation framework implemented with PyTorch
Stars: ✭ 33 (-29.79%)
Mutual labels:  cnn
Face Identification With Cnn Triplet Loss
Face identification with cnn+triplet-loss written by Keras.
Stars: ✭ 45 (-4.26%)
Mutual labels:  cnn
Qanet
A Tensorflow implementation of QANet for machine reading comprehension
Stars: ✭ 996 (+2019.15%)
Mutual labels:  cnn
Chineseidcardocr
[Deprecated] 🇨🇳中国二代身份证光学识别
Stars: ✭ 1,015 (+2059.57%)
Mutual labels:  cnn
Twitter Sentiment Analysis
Sentiment analysis on tweets using Naive Bayes, SVM, CNN, LSTM, etc.
Stars: ✭ 978 (+1980.85%)
Mutual labels:  cnn
Mc Cnn Python
a python implementation of MC-CNN
Stars: ✭ 38 (-19.15%)
Mutual labels:  cnn
Yann
This toolbox is support material for the book on CNN (http://www.convolution.network).
Stars: ✭ 41 (-12.77%)
Mutual labels:  cnn
Neural Networks
All about Neural Networks!
Stars: ✭ 34 (-27.66%)
Mutual labels:  cnn
Svhn Cnn
Google Street View House Number(SVHN) Dataset, and classifying them through CNN
Stars: ✭ 44 (-6.38%)
Mutual labels:  cnn
Deepmodels
TensorFlow Implementation of state-of-the-art models since 2012
Stars: ✭ 33 (-29.79%)
Mutual labels:  cnn
Dialectid e2e
End to End Dialect Identification using Convolutional Neural Network
Stars: ✭ 40 (-14.89%)
Mutual labels:  cnn
Vgn
Deep Vessel Segmentation by Learning Graphical Connectivity
Stars: ✭ 46 (-2.13%)
Mutual labels:  cnn
Cortex M Kws
Cortex M KWS example with Tengine Lite.
Stars: ✭ 45 (-4.26%)
Mutual labels:  cnn
Neural Style
本代码加入了神经风格迁移中文注释，更易理解，同时新加入begin.py可直接运行调试。
Stars: ✭ 42 (-10.64%)
Mutual labels:  cnn
View All Similar Projects ➔

DVDnet

A state-of-the-art, simple and fast network for Deep Video Denoising

NEW: a state-of-the-art algorithm for video denoising without motion compensation FastDVDnet

Overview

This source code provides a PyTorch implementation of DVDnet image denoising, as in Tassano, Matias and Delon, Julie and Veit, Thomas. "DVDnet: A Fast Network for Deep Video Denoising", IEEE ICIP 2019, arXiv preprint arXiv:1906.11890 (2019).

Video examples

You can download several denoised sequences with our algorithm and other methods here

User Guide

The code as is runs in Python +3.6 with the following dependencies:

Dependencies

Usage

If you want to denoise an image sequence using the pretrained models found under the models folder you can execute

python test_dvdnet.py \
        --test_path <path_to_input_sequence> \
	--save_path results \
        --noise_sigma 25 \

NOTES

  • The image sequence should be stored under <path_to_input_sequence>
  • Models have been trained for values of noise in [5, 55]
  • run with --no_gpu to run on CPU instead of GPU
  • run with --save_noisy to save noisy frames
  • set max_num_fr_per_seq to set the max number of frames to load per sequence
  • run with --help to see details on all input parameters

Comparison of PSNRs

Two different testsets were used for benchmarking our method: the DAVIS-test testset, and Set8, which is composed of 4 color sequences from the Derf’s Test Media collection and 4 color sequences captured with a GoPro camera. The DAVIS set contains 30 color sequences of resolution 854 x 480. The sequences of Set8 have been downscaled to a resolution of 960 x 540. In all cases, sequences were limited to a maximum of 85 frames. We used the DeepFlow algorithm to compute flow maps for DVDnet and VNLB. For Neat Video, the automatic noise profiling settings were used.

Note: values shown are the average for all sequences in the testset, the PNSR of a sequence is computed as the average of the PSNRs of each frame.

PSNRs Set8 testset

Noise std dev DVDNet VNLB [1] V-BM4D [2] Neat Video [3]
10 36.08 37.26 36.05 35.67
20 33.49 33.72 32.19 31.69
30 31.79 31.74 30.00 28.84
40 30.55 30.39 28.48 26.36
50 29.56 29.24 27.33 25.46

PSNRs DAVIS testset

Noise std dev DVDNet VNLB V-BM4D
10 38.13 38.85 37.58
20 35.70 35.68 33.88
30 34.08 33.73 31.65
40 32.86 32.32 30.05
50 31.85 31.13 28.80

ABOUT

Copying and distribution of this file, with or without modification, are permitted in any medium without royalty provided the copyright notice and this notice are preserved. This file is offered as-is, without any warranty.

  • Author : Matias Tassano matias dot tassano at parisdescartes dot fr
  • Copyright : (C) 2019 Matias Tassano
  • Licence : GPL v3+, see GPLv3.txt

The sequences are Copyright GoPro 2018

References

[1] P. Arias and J.-M. Morel, “Video denoising via empirical Bayesian estimation of space-time patches,” Journal of Mathematical Imaging and Vision, vol. 60, no. 1, pp. 70—-93, 2018

[2] M. Maggioni, G. Boracchi, A. Foi, K. Egiazarian, “Video denoising, deblocking, and enhancement through separable 4-D nonlocal spatiotemporal transforms,” IEEE Trans. IP, vol. 21, no. 9, pp. 3952–3966, 2012.

[3] ABSoft, “Neat Video,” https://www.neatvideo.com, 1999–2019.

Note that the project description data, including the texts, logos, images, and/or trademarks, for each open source project belongs to its rightful owner. If you wish to add or remove any projects, please contact us at [email protected].