gfacciol / bm3d Goto Github PK
View Code? Open in Web Editor NEWLicense: GNU General Public License v3.0
License: GNU General Public License v3.0
% BM3D image denoising. # ABOUT * Author : Marc Lebrun <[email protected]> * Copyright : (C) 2011 IPOL Image Processing On Line http://www.ipol.im/ * Licence : GPL v3+, see GPLv3.txt # OVERVIEW This source code provides an implementation of the BM3D image denoising. # UNIX/LINUX/MAC USER GUIDE The code is compilable on Unix/Linux and Mac OS. - Compilation. Automated compilation requires the cmake program. - Libraries. This code requires the libpng libtiff libjpeg and libfftw librarers. - Image formats. PNG, JPEG, TIFF (including floating point) formatis is supported. ------------------------------------------------------------------------- Usage: 1. Download the code package and extract it. Go to that directory. 2. Compile the source code (on Unix/Linux/Mac OS). mkdir build; cd build; cmake ..; make 3. Run BM3D image denoising. ./bm3d The generic way to run the code is: ./bm3d input.png sigma ImDenoised.png [ImBasic.png ] -tau_2d_hard 2DtransformStep1 -useSD_hard -tau_2d_wien 2DtransformStep2 -useSD_wien -color_space ColorSpace with : - cinput.png is a noisy image; - sigma is the value of the noise; - ImBasic.png will contain the result of the first step of the algorithm; - ImDenoised.png will contain the final result of the algorithm; - 2DtransformStep1: choice of the 2D transform which will be applied in the second step of the algorithm. You can choose the DCT transform or the Bior1.5 transform for the 2D transform in the step 1 (tau_2D_hard = dct or bior) and/or the step 2. (tau_2d_wien = dct or bior). - useSD_hard: for the first step, users can choose if they prefer to use standard variation for the weighted aggregation (useSD1 = 1) - 2DtransformStep2: choice of the 2D transform which will be applied in the second step of the algorithm. You can choose the DCT transform or the Bior1.5 transform for the 2D transform in the step 1 (tau_2D_hard = dct or bior) and/or the step 2. (tau_2d_wien = dct or bior). - useSD_wien: for the second step, users can choose if they prefer to use standard variation for the weighted aggregation (useSD2 = 1) - ColorSpace: choice of the color space on which the image will be applied. you can choose the colorspace for both steps between : rgb, yuv, ycbcr and opp. - patch_size: overrides the default patch size - nb_threads: specifies the number of working threads - verbose: print additional information Example, run ./BM3Ddenoising cinput.png 10 ImDenoised.png ImBasic.png -useSD_wien \ -tau_2d_hard bior -tau_2d_wien dct -color_space opp # ABOUT THIS FILE Copyright 2011 IPOL Image Processing On Line http://www.ipol.im/ 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.
I am really liking the pybm3d wrapper. Thanks! Is there any motivation on your side of things to implement a pybm4d for image cubes?
Line 1341 in 5c86dfe
//! Threshold distances in order to keep similar patches
for (int dj = -(int) nHW; dj <= (int) nHW; dj++)
{
for (int di = 0; di <= (int) nHW; di++)
if (sum_table[dj + nHW + di * Ns][k_r] < threshold)
table_distance.push_back(make_pair(
sum_table[dj + nHW + di * Ns][k_r]
, k_r + di * width + dj));
for (int di = - (int) nHW; di < 0; di++)
if (sum_table[-dj + nHW + (-di) * Ns][k_r] < threshold)
table_distance.push_back(make_pair(
sum_table[-dj + nHW + (-di) * Ns][k_r + di * width + dj]
, k_r + di * width + dj));
}
This is very suspicious. Since dj takes the same negative and positive values, it means the second if test is a duplicate of the first one, however it doesn't insert the same element. Wrong check ?
Dear
Is there any error in line 1375?
for (int di = - (int) nHW; di < 0; di++)
if (sum_table[-dj + nHW + (-di) * Ns][k_r + di * width + dj] < threshold)**
table_distance.push_back(make_pair(
sum_table[-dj + nHW + (-di) * Ns][k_r + di * width + dj]
, k_r + di * width + dj));
nantest.zip
I've found some images (typically mono images with mostly low pixel values and high dynamic range, such as unstretched astronomical images, when processed with BM3D, generate blocks of -nan in the output. Looking at the basic output, the -nan values appear to start off in the first stage of the algorithm usually as single pixels and then presumably get spread to a whole block in the second stage where processing of a block encounters the pixel with -nan value. An example file that creates -nan results is attached: the sigma for this file is 0.000105 (using bgnoise measurement from Siril).
The ./bm3d
executable seems to have a problem with saving an image in the JPG format. I tried to denoise this image which worked only if I set the output filename to *.png
but not *.jpg
. The denoising seems to work in both cases but for the latter the saved image can not be opened.
In bm3d.cpp, lines 272, 304, 307 and 341 seem to do the following:
Shouldn't the values of N for chopping the image up and reassembling it be the same? In practice it doesn't matter because nWien and nHard are both defined as the same value, but if one value was changed it seems the result would not be good. I think the parameters on those lines should respectively be 2 * nHard, 2 * nHard, 2 * nWien, 2 * nWien.
Hi, I'm little confused about the value of tauMatch (function bm3d_1st_step):
const float tauMatch = (chnls == 1 ? 3.f : 1.f) * (sigma_table[0] < 35.0f ? 2500 : 5000)
I'm just wondering why do we use tauMatch = 3\sigma when the input image has single channel?
Thank you!
I work with large 32 bits floating point TIFF. The code works great with 1000x1000 pixels images, while with larger ones (e.g. 5000x5000, 10000x10000) it uses the 99%-100% of the RAM (32GB) making the entire system unresponsive for several hours (16+ hours) and in the end terminating the process uncompleted.
I use other noise reduction algorithms on such images, but it is the first time I've this kind of problem.
Any suggestion or indication? Perhaps some parameter to set or similar? Is the code suitable for images larger than 1000x1000?
Thank you.
A declarative, efficient, and flexible JavaScript library for building user interfaces.
๐ Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. ๐๐๐
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google โค๏ธ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.