FFT3DFilter v2.10

FFT3DFilter v2.2.10 (20211018)

• Fix possible crash on exit on ncpu=1 (uninitialized fft3w threads)
• Fix C version (possibly unused on Intel builds, when CPU less than SSE2) in sharpen+degrid method

FFT3DFilter v2.9

FFT3DFilter v2.9 (20210324)

• Fix issue when pfactor <> 0 and using 10+ bits (Xinyue Lu, neo_FFT3D)
• Fix incorrect negative value float to integer rounding (Xinyue Lu, neo_FFT3D r7)
• add CMake build system
• linux build
• Replace never used 3dnow ApplyWiener3D4 with simd SSE2. (bt=4, degrid=0, pfactor=0) (2x speed)

FFT3DFilter v2.8

FFT3DFilter v2.8 (20201201)

• Fix: chroma plane filtering for 32 bit float formats

FFT3DFilter v2.7 (20201130)

• Fix: make fftw plans thread safe.
• preserve frame properties for avs+

FFT3DFilter v2.7

fft3dfilter

FFT3DFilter v2.7 (20201130)

• Fix: make fftw plans thread safe.
• preserve frame properties for avs+

FFT3DFilter v2.6

fft3dfilter

Change log

FFT3DFilter v2.6 (20190131)
  - Fix: Proper rounding when internal 32 bit float data are converted back to integer pixel values

FFT3DFilter v2.5 (20180702)
  - 32bit Float YUV: Chroma center to 0.0 instead of 0.5, to match new Avisynth+ r2728-

FFT3DFilter v2.4 (20170608)
  - some inline asm (not all) ported to simd intrisics, helps speedup x64 mode, but some of them faster also on x86.
  - intrinsics bt=0 
  - intrinsics bt=2, degrid=0, pfactor=0
  - intrinsics bt=3 sharpen=0/1 dehalo=0/1
  - intrinsics bt=3
  - Adaptive MT settings for Avisynth+: MT_SERIALIZED for bt==0 (temporal), MT_MULTI_INSTANCE for others
  - Copy Alpha plane if exists
  - reentrancy checks against bad multithreading usage
    Note: for properly operating in MT_SERIALIZED mode in Avisynth MT, please use Avs+ r2504 or better.

FFT3DFilter v2.3 (20170221)
  - apply current avs+ headers
  - 10-16 bits and 32 bit float colorspace support in AVS+
  - Planar RGB support
  - look for libfftw3f-3.dll first, then fftw3.dll
  - inline asm ignored on x64 builds
  - pre-check: if plane to process for greyscale is U and/or V return original clip
  - auto register MT mode for avs+: MT_SERIALIZED

Previous versions by Fizick and martin53

Original Docs:
https://avisynth.org.ru/fft3dfilter/fft3dfilter.html
Project:
https://github.com/pinterf/fft3dfilter
Forum:
https://forum.doom9.org/showthread.php?t=174347

FFT3DFilter v2.5

FFT3DFilter v2.4

Change log

FFT3DFilter v2.5 (20180702)
  - 32bit Float YUV: Chroma center to 0.0 instead of 0.5, to match new Avisynth+ r2728-

FFT3DFilter v2.4 (20170608)
  - some inline asm (not all) ported to simd intrisics, helps speedup x64 mode, but some of them faster also on x86.
  - intrinsics bt=0 
  - intrinsics bt=2, degrid=0, pfactor=0
  - intrinsics bt=3 sharpen=0/1 dehalo=0/1
  - intrinsics bt=3
  - Adaptive MT settings for Avisynth+: MT_SERIALIZED for bt==0 (temporal), MT_MULTI_INSTANCE for others
  - Copy Alpha plane if exists
  - reentrancy checks against bad multithreading usage
    Note: for properly operating in MT_SERIALIZED mode in Avisynth MT, please use Avs+ r2504 or better.

FFT3DFilter v2.3 (20170221)
  - apply current avs+ headers
  - 10-16 bits and 32 bit float colorspace support in AVS+
  - Planar RGB support
  - look for libfftw3f-3.dll first, then fftw3.dll
  - inline asm ignored on x64 builds
  - pre-check: if plane to process for greyscale is U and/or V return original clip
  - auto register MT mode for avs+: MT_SERIALIZED

Previous versions by Fizick and martin53

Original Docs:
https://avisynth.org.ru/fft3dfilter/fft3dfilter.html
Project:
https://github.com/pinterf/fft3dfilter
Forum:
https://forum.doom9.org/showthread.php?t=174347

FFT3DFilter v2.4, experimental high bit depth/x64 support

FFT3DFilter v2.4

Change log

FFT3DFilter v2.4 (20170608)
  - some inline asm (not all) ported to simd intrisics, helps speedup x64 mode, but some of them faster also on x86.
  - intrinsics bt=0 
  - intrinsics bt=2, degrid=0, pfactor=0
  - intrinsics bt=3 sharpen=0/1 dehalo=0/1
  - intrinsics bt=3
  - Adaptive MT settings for Avisynth+: MT_SERIALIZED for bt==0 (temporal), MT_MULTI_INSTANCE for others
  - Copy Alpha plane if exists
  - reentrancy checks against bad multithreading usage
    Note: for properly operating in MT_SERIALIZED mode in Avisynth MT, please use Avs+ r2504 or better.

FFT3DFilter v2.3 (20170221)
  - apply current avs+ headers
  - 10-16 bits and 32 bit float colorspace support in AVS+
  - Planar RGB support
  - look for libfftw3f-3.dll first, then fftw3.dll
  - inline asm ignored on x64 builds
  - pre-check: if plane to process for greyscale is U and/or V return original clip
  - auto register MT mode for avs+: MT_SERIALIZED

Previous versions by Fizick and martin53

Original Docs:
https://avisynth.org.ru/fft3dfilter/fft3dfilter.html
Project:
https://github.com/pinterf/fft3dfilter
Forum:
https://forum.doom9.org/showthread.php?t=174347

FFT3DFilter v2.3, experimental high bit depth support

FFT3DFilter v2.3

Experimental release, supporting for avisynth+ new color spaces

• apply current avs+ headers
• 10-16 bits and 32 bit float colorspace support in AVS+
• Planar RGB support
• look for libfftw3f-3.dll first, then fftw3.dll
• inline asm ignored on x64 builds
• pre-check: if plane to process for greyscale is U and/or V then returns original clip
• auto register MT mode for avs+: MT_SERIALIZED
• autoscale sigma and smin/smax parameter from 8 bit scale if colorspace is different
• x64 friendly code (ignore inline asm)