fastdvdnet

reparied the version on DALI loader

change model's input on 3 continues images

FastDVDnet

A state-of-the-art, simple and fast network for Deep Video Denoising which uses no motion compensation.

NEW: Paper to be presented at CVPR2020

Previous deep video denoising algorithm: DVDnet

Overview

This source code provides a PyTorch implementation of the FastDVDnet video denoising algorithm, as in Tassano, Matias and Delon, Julie and Veit, Thomas. "FastDVDnet: Towards Real-Time Video Denoising Without Explicit Motion Estimation", arXiv preprint arXiv:1907.01361 (2019).

Video Examples

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

Running Times

FastDVDnet is orders of magnitude faster than other state-of-the-art methods

User Guide

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

Dependencies

Note: the tested version of NVIDIA DALI is 0.10.0. To install it (supposing you have CUDA 10.0), you need to run

pip install --extra-index-url https://developer.download.nvidia.com/compute/redist/cuda/10.0 nvidia-dali==0.10.0

Usage

Testing

If you want to denoise an image sequence using the pretrained model you can execute

test_fastdvdnet.py \
	--test_path <path_to_input_sequence> \
	--noise_sigma 30 \
	--save_path results

NOTES

The image sequence should be stored under <path_to_input_sequence>
The model has 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
to denoise clipped AWGN run with --model_file model_clipped_noise.pth
run with --help to see details on all input parameters

Training

If you want to train your own models you can execute

train_fastdvdnet.py \
	--trainset_dir <path_to_input_mp4s> \
	--valset_dir <path_to_val_sequences> \
	--log_dir logs