RUSSIAN

VirtualDub MSU Denoising Filter
(Noise Removal)

MSU Graphics & Media Lab (Video Group)

Algorithm, ideas: Dr. Dmitriy Vatolin, Dmitriy Kulikov
Implementation: Sergey Putilin, Ilya Tsvetkov

Version 2.5 released

The filter is designed for noisy video stream processing, video quality improvement, or video preprocessing (e.g. for preprocessing before compression or deinterlacing). The filter implementation is able to use GPU processing power to increase the processing speed.

DOWNLOAD PURCHASE
Free version for non-commercial home usage only License for commercial or professional usage


Change log


Version 2.5
  • New algorithm for high definition video (HDTV) processing added
  • Automatic noise estimation
  • Shot detection to reduce artifacts during temporal denoising
  • Cg libraries are not used any more
Version 2.0 beta
  • First version with support for fast video processing using GPU
  • New interface

Settings


By default filter uses automatic noise estimation and is ready for video processing without any manual setup. In this mode user can slightly correct denosing strength to achieve necessary results Automatic noise estimation checkbox controls this mode.

Внешний вид фильтра

Setting the checkbox you can select GPU or CPU versions of algorithm.
Source frame with noise
GPU-mode is available, so you can use GPU for video processing (this feature is optional)
LUV metric for frames 13 and 14
GPU-mode is unavailable. The most probable reason is that your computer does not meet the minimum system requirements of the filter

Note that not all graphic-cards are supported. We recommend to use ATI Radeon X700 or higher and nVidia Geforce 6600 or higher. The filter requires OpenGL 2.1 support. We strongly recommend to install the latest video-drivers to use GPU-mode and achieve better performance.

Filter provides two different algorithms for video denoising (selection is made via Algorithms list):

  • MSU Denoiser - algorithm used in previous versions of filter
  • Внешний вид фильтра

    The filter suppresses noise in both spatial and temporal domains. Filter effect is specified for each type of denoising in the dialogue box as shown. Checkboxes help to set required combination of domains, thus enabling spatial-only or temporal-only denoising.

    The new feature of 2.5 release is careful scene change processing. The filter detects shots to prevent artifacts of temporal denoising, but can also reduce the performance, especially when high performance GPU is used.

  • Bilateral - new algorithm which is implemented in three variants corresponding to different performance/quality ratios. This algorithm is most suitable for HD video denoising because of its quality.
  • Внешний вид фильтра

Filter supports Job Control and can be used with AviSynth. Here is an example:

LoadVirtualDubPlugin("..\VirtualDub\plugins\MSUDenoiser25.vdf", "MSUDenoiser", 1)
clip = AviSource("video.avi")
clip.ConvertToRGB32.MSUDenoiser(algorithm, gpuMode, correction, shotDetection)

Parameters:

  • algorithm: 0 - MSU Denoiser; 1 - Bilateral, small region (fast); 2 - Bilateral, medium; 3 - Bilateral, big region (best quality);
  • gpuMode - if set to 0, CPU is used; GPU otherwise;
  • correction - manual correction for automatic mode (50 - no correction);
  • shotDetection - careful scene change processing (for MSU Denoiser algorithm only).

Examples


Let's consider filter operation on Susy sequence first. The sequence is quite noisy in spatial and temporal domains.
Let's compare source frame with the frame processed by MSU Denoising Filter:

Source frame with noise
Source frame with noise
Frame processed by MSU Denoising Filter
Frame processed by MSU Denoising Filter
(made with 'hard' preset that emphasizes filter effect)


Performance comparison


Here is a comparison between two versions of MSU Denoiser: old version without GPU processing and new version with GPU processing
A fragment of source frame
Comparison of filter processing speed on different hardware
A fragment of source frame
Increase of performance speed compared with CPU (Pentium 4 3.4 GHz) version of algorithm

Installation


To use the filter download the archive using the link given below and extract its content into VitualDub plugins directory.


Download


  • Filter for Virtual Dub
  • Version 2.5 with GPU processing (112 KB, ZIP)
    GPU usage provides up to 7 times processing speed increase
  • Previous version 2.0 beta (1.2 MB, ZIP)
  • Version 1.61 without GPU processing (80 KB, ZIP)
  • Documentation
  • New! Comparison of video denoisers, 2007
  • Description and comparison of noise suppression methods used in other available filters.
  • Description of MSU Denoising (free) & MSU Noise Removal filters.
    In this report we show how MSU Noise Removal usage can increase compression up to 30% with better (!) visual quality.
  • Licenses
  • Program license for non-commercial usage
  • Program license for usage in companies
    If you have discount code (e.g. as successful tester) please use this form
  • E-mail:
    For common questions about filter's work please contact us
    For commercial license of this filter (commercial usage is not free) please contact us сontact email


    Other resources


    Video resources:

    Last updated: 12-May-2022


    Server size: 8069 files, 1215Mb (Server statistics)

    Project updated by
    Server Team and MSU Video Group

    Project sponsored by YUVsoft Corp.

    Project supported by MSU Graphics & Media Lab