# FFT3DGPU

(v0.8.6) |
(add precision note and fix a typo) |
||

Line 70: | Line 70: | ||

<br> | <br> | ||

::{{Par2|bordersize|int|1}} | ::{{Par2|bordersize|int|1}} | ||

− | :::Only used with < | + | :::Only used with <code>mode</code> 2. Defines the size of the border. |

<br> | <br> | ||

::{{Par2|precision|int|0}} | ::{{Par2|precision|int|0}} | ||

:::*0 : to use 16 bit floats(half precision). | :::*0 : to use 16 bit floats(half precision). | ||

− | :::* 1 : to use 32 bit float(single precision) for the fft and 16 bit float for the wienner/kalman and sharpening. | + | :::*1 : to use 32 bit float(single precision) for the fft and 16 bit float for the wienner/kalman and sharpening. |

:::*2 : always use 32 bit floats. | :::*2 : always use 32 bit floats. | ||

:::Using 16 bit float increases the performance but reduces precision. With a Geforce 7800GT precision=0 is ~1.5 times faster than than mode 2. | :::Using 16 bit float increases the performance but reduces precision. With a Geforce 7800GT precision=0 is ~1.5 times faster than than mode 2. | ||

+ | :::Note: in FFT3dGPU v0.8.6, for 10-32 bit clips, the parameter "precision" is ignored and is set to 2: always use 32 bit float internally. | ||

<br> | <br> | ||

::{{Par2|NVPerf|bool|false}} | ::{{Par2|NVPerf|bool|false}} |

## Latest revision as of 17:48, 18 September 2021

Abstract | |
---|---|

Author | tsp, pinterf |

Version | v0.8.6 |

Download | FFT3dGPU-v0.8.6-pfmod.7z |

Category | Denoisers |

License | GPLv2 |

Discussion | Doom9 Forum (original) |

## Contents |

## [edit] Description

FFT3dGPU is a GPU version of Fizick's FFT3DFilter. The algorithm (Fast Fourier Transform, denoising) is the same for the most part. Currently the following is not implemented: support for noise pattern.

In this version the next frame is processed while waiting for the GPU to end it's work. Meaning the filters before fft3dGPU are working concurrently with it. From v0.8.4, the filter automatically registers itself as MT_SERIALIZED for AviSynth+.

## [edit] Requirements

- [x86]: AviSynth+ or AviSynth 2.6.0
- [x64]: AviSynth+
- Supported color formats: Y8, YV12, YV16, YV24, YV411
- AviSynth+: All planar formats (8/10/12/14/16/32-bit, YUV/RGB with or without alpha) are supported.

## [edit] Syntax and Parameters

FFT3DGPU (clip, float "sigma", float "beta", int "bw", int "bh", int "bt", float "sharpen", int "plane", int "mode", int "bordersize", int "precision", bool "NVPerf", float "degrid", float "scutoff", float "svr", float "smin", float "smax", float "kratio", int "ow", int "oh", int "wintype" , int "interlaced", float "sigma2", float "sigma3", float "sigma4", bool "oldfft")

*clip*=

- Input clip

*float*sigma =*2.0*

- Given noise value for all (or highest) frequencies. Only values greater that 0.0

*float*beta =*1.0*

- Noise margin (float>=1.0, default=1.0 for no noise left): control noise amount left in the restoration for Wiener filter, so max filter noise attenuation =
`(beta-1)/beta`

.

- Noise margin (float>=1.0, default=1.0 for no noise left): control noise amount left in the restoration for Wiener filter, so max filter noise attenuation =

*int*bw =*32*

*int*bh =*32*

- Block width and height. It should be a power of 2 ie valid values is 4,8,16,32,64,128,256,512 (note that
`bw`

should be greater than 4 for best result).

- Block width and height. It should be a power of 2 ie valid values is 4,8,16,32,64,128,256,512 (note that

*int*bt =*3*

- Block temporal size, number of frames.
- -1 : sharpen only (2D)
- 0 : all previous frames (switch Kalman filter mode)
- 1 : only current frame (spatial 2D Wiener filter)
- 2 : previous and current frame (3D Wiener filter)
- 3 : previous, current and next frame (3D Wiener filter)
- 4 : two previous, current and next frame (3D Wiener filter)

- Block temporal size, number of frames.

*float*sharpen =*0.0*

- Sharpening strength, positive values sharpens the image, negative values blurs the image. 0 disables sharpening.

*int*plane =*0*

- Processed color plane:
- 0 : luma(Y)
- 1 : chroma U
- 2 : chroma V
- 3 : chroma planes U and V
- 4 : both luma and chroma

- For a greyscale clip. 4 means luma (the only plane), 1,2 and 3 gives error message.
- For RGB clips (planar RGB only!) operation is always 4=all planes, regardless of this parameter.

- Processed color plane:

*int*mode =*1*

- Processing mode:
- 0 : only overlaps 1:1. This is faster but produces artifacts with high sigma values.
- 1 : block overlaps 2:1. This is slower but produces fewer artifacts.
- 2 : again 1:1 overlap but with a additional border. This reduces border artifacts seen with mode=0.

- The speed is between mode 0 and 1.
`Kalman(bt=0)`

works well with`mode=0`

.

- Processing mode:

*int*bordersize =*1*

- Only used with
`mode`

2. Defines the size of the border.

- Only used with

*int*precision =*0*

- 0 : to use 16 bit floats(half precision).
- 1 : to use 32 bit float(single precision) for the fft and 16 bit float for the wienner/kalman and sharpening.
- 2 : always use 32 bit floats.

- Using 16 bit float increases the performance but reduces precision. With a Geforce 7800GT precision=0 is ~1.5 times faster than than mode 2.
- Note: in FFT3dGPU v0.8.6, for 10-32 bit clips, the parameter "precision" is ignored and is set to 2: always use 32 bit float internally.

*bool*NVPerf =*false*

- Enables support for NVPerfHUD (http://developer.nvidia.com/object/nvperfhud_home.html).

*float*degrid =*1.0*

- Enables degriding. Only works well with
`mode=1`

. Doesn't degrid the Kalman filter (but it does degrid the sharpening (if enabled) after kalman filter). default 1.0 for`mode=1`

, 0.0 for`mode=0`

or 2.

- Enables degriding. Only works well with

*float*scutoff =*0.3*

- Sharpening cutoff frequency, relative to max.

*float*svr =*1.0*

- Sharpening (and dehalo) vertical ratio (to horizontal) (default=1.0 - same as horizontal, 0 - no vertical sharpening)

*float*smin =*4.0*

*float*smin =*20.0*

- Minimum and maximum limit (approximate noise margin) for sharpening stage.

*float*kratio =*2.0*

- Ratio of threshold to sigma to reset Kalman filter. Variation threshold =
`sigma*kratio`

, good value is about from 1.5 to 3.0

- Ratio of threshold to sigma to reset Kalman filter. Variation threshold =

*int*ow =*bw/2*

*int*oh =*bh/2*

- Overlap width and height. This only works with
`mode=1`

. This specifies how big the overlap between the blocks are. Overlap size must be less than or equal to half the blocksize.`ow`

must be even.

- Overlap width and height. This only works with

*int*wintype =*0*

- weighting windows type:
- 0 : same analysis and synthesis half-cosine window, used in all versions before 1.4.
- 1 : intermediate between 0 and 2
- 2 : flat analysis window, rised cosine (Hanning) synthesis window.

- weighting windows type:

*bool*interlaced =*false*

- Set to true for separate filtering for each field.

*float*singma2 =*sigma*

*float*singma3 =*sigma*

*float*singma4 =*sigma*

- Given noise value at second, third, and lowest scale level frequencies. Only values greater that 0.0

*bool*oldfft =*false*

- Set to true to use the old fftcode (used in version 0.6.2 and lower) false to use new fft code. If not defined fft3dgpu will use the fastest code.

## [edit] Changelog

Version Date Changes

v0.8.6 2021/01/04 - Support 10-32 bit formats. Parameter ranges (smin, smax, sigmas) are the same for all bit depths. - For 10-32 bit clips parameter "precision" is ignored and is set to 2: always use 32 bit float internally - Note: for 8 bits "precision" default is 0: calculation is done in 16 bit floating point type (s10m5) internally

v0.8.5 2020/11/01 - Avisynth+ 3.6 additional support: preserve frame properties - Fix bt=0 Kalman mode warning in fft3dgpu.hlsl

v0.8.4 2018/11/21 - New color spaces besides YV12 and YUY2: Y8, YV16, YV411, YV24 (all 8 bits), 8 bit Planar RGB (AviSynth+) - FFT3dGPU filter registers itself as MT_SERIALIZED automatically for AviSynth+: no need for SetFilterMTMode.

v0.8.3 2018/11/18 - project hosted on https://github.com/pinterf/FFT3dGPU - source and project files updated to build under Visual Studio 2017 - (15.9) using DX SDK June 2010 - Moved to Avisynth Interface 6 (v2.6) - using headers from the AviSynth+ project - added x64 platform

v0.8.2a 2006/08/24 - Last release by tsp, see included docs for full changelog

## [edit] Archived Downloads

Version | Download | Mirror |
---|---|---|

v0.8.2a | fft3dgpu0.8.2a.exe | fft3dgpu0.8.2a.exe |

v0.8.2 (x64) | FFT3DGPU_3-15-2010.rar | FFT3DGPU_3-15-2010.rar |

v0.8.2 | fft3dgpu0.8.2.7z /// fft3dgpu0.8.2.exe | fft3dgpu0.8.2.7z /// fft3dgpu0.8.2.exe |

- v0.8.2 x64 version compiled by Joshy D.

## [edit] External Links

**Back to External Filters ←**