VMAF: Difference between revisions

From Avisynth wiki
Jump to navigationJump to search
Newer edit →

Asd (talk | contribs)

113 edits
VMAF v1.0.0
 
Asd (talk | contribs)
113 edits
Update to the latest version
Line 2: Line 2:
{{Filter3
{{Filter3
| 1={{Author/Asd-g}}
| 1={{Author/Asd-g}}
| 2=v1.0.0
| 2=v2.1.0
| 3=[https://github.com/Asd-g/AviSynth-VMAF/releases/ VMAF-1.0.0.7z]
| 3=[https://github.com/Asd-g/AviSynth-VMAF/releases/ VMAF]
| 4=Debug filter
| 4=Debug filter
| 5=[https://github.com/Asd-g/AviSynth-VMAF/blob/main/LICENSE MIT]
| 5=[https://github.com/Asd-g/AviSynth-VMAF/blob/main/LICENSE MIT]
Line 13: Line 13:
This is [https://github.com/HomeOfVapourSynthEvolution/VapourSynth-VMAF a port of the VapourSynth plugin VMAF.]
This is [https://github.com/HomeOfVapourSynthEvolution/VapourSynth-VMAF a port of the VapourSynth plugin VMAF.]


[https://github.com/Netflix/vmaf/tree/v1.3.15 vmaf] is used.
[https://github.com/Netflix/vmaf vmaf] is used.
<br>
<br>
<br>
<br>
Line 21: Line 21:
* Supported color formats: [[Y8]], [[YV12]], [[YV16]], [[YV24]], [[YV411]]
* Supported color formats: [[Y8]], [[YV12]], [[YV16]], [[YV24]], [[YV411]]
**AviSynth+: all [[planar]] Y and YUV formats (8/10/12/14/16bit) are supported.
**AviSynth+: all [[planar]] Y and YUV formats (8/10/12/14/16bit) are supported.
<br>
'''NOTE:'''The folder <code>model</code> must be located in the same folder as <code>VMAF.dll</code>.
<br>
<br>
<br>
<br>
== [[Script variables|Syntax and Parameters]] ==
== [[Script variables|Syntax and Parameters]] ==
:{{Template:FuncDef|VMAF (clip reference, clip distorted, int "model", string "log_path", int "log_fmt", bool "ssim", bool "ms_ssim", int "pool", bool "ci")}}
:{{Template:FuncDef|VMAF (clip reference, clip distorted, string log_path, int "log_format", int[] "model", int[] "feature", string "cambi_opt")}}
<br>
<br>
::{{Par2| |clip| }}
::{{Par2| |reference| }}
::{{Par2| |clip| }}
::{{Par2| |distorted| }}
::: Clips to calculate VMAF score. Must be in YUV 8..16-bit planar format.
::: Clips to calculate VMAF score. Must be in YUV 8..16-bit planar format.
::: First input clip is the reference, second input clip is the distorted clip (e.g. processed, encoded, etc).
::: Must be in YUV 8..16-bit planar format with minimum three planes.
<br>
::{{Par2|model|int|0}}
:::Sets which model to use. Refer to the [https://github.com/Netflix/vmaf/blob/v1.3.15/resource/doc/models.md models] page for more details.
:::*0: vmaf_v0.6.1.pkl
:::*1: vmaf_4k_v0.6.1.pkl
:::Default: 0.
<br>
<br>
::{{Par2|log_path|string|}}
::{{Par2|log_path|string|}}
:::Sets the path of the log file.
:::Sets the path of the log file.
:::Default: None.
<br>
<br>
::{{Par2|log_fmt|int|0}}
::{{Par2|log_format|int|0}}
:::Sets the format of the log file.
:::Sets the format of the log file.
:::*0: xml.
:::*0 : xml.
:::*1: json.
:::*1 : json.
:::*2: csv.
:::*2 : csv.
:::Default: 0.
<br>
<br>
::{{Par2|ssim|bool|false}}
::{{Par2|model|int[]|}}
:::Whether to also calculate SSIM score.
:::Sets which model to use. Refer to [https://github.com/Netflix/vmaf/blob/master/resource/doc/models.md this], [https://netflixtechblog.com/toward-a-better-quality-metric-for-the-video-community-7ed94e752a30 this] and [https://github.com/Netflix/vmaf/blob/master/resource/doc/conf_interval.md this] page for more details.
:::Default: False.
:::*0 : vmaf_v0.6.1
:::*1 : vmaf_v0.6.1neg (NEG mode)
:::*2 : vmaf_b_v0.6.3 (Confidence Interval)
:::*3 : vmaf_4k_v0.6.1
<br>
<br>
::{{Par2|ms_ssim|bool|false}}
::{{Par2|feature|int[]|}}
:::Whether to also calculate MS-SSIM score.
:::*0 : PSNR
:::Default: False.
:::*1 : PSNR-HVS
:::*2 : SSIM
:::*3 : MS-SSIM
:::*4 : CIEDE2000
:::*5 : CAMBI
<br>
<br>
::{{Par2|pool|int|1}}
::{{Par2|cambi_opt|string|}}
:::Sets the method to pool the per-frame scores.
:::* enc_width, enc_height
:::*0: Mean.
:::: Encoding/processing resolution to compute the banding score, useful in cases where scaling was applied to the input prior to the computation of metrics.
:::*1: Harmonic mean.
:::: enc_width must be between 320 and 7680.
:::*2: Min.
:::: enc_height must be between 200 and 4320.
:::Default: 1.
:::: Default: Same as input image.
<br>
:::* window_size
::{{Par2|ci|bool|false}}
:::: Window size to compute CAMBI.
:::Whether to enable confidence interval.
:::: Must be between 15 and 127.
:::True: It uses vmaf_b_v0.6.3 for model=0 and vmaf_4k_rb_v0.6.2 for model=1.
:::: Default: 63 (corresponds to ~1 degree at 4K resolution and 1.5H).
:::Refer to the [https://github.com/Netflix/vmaf/blob/v1.3.15/resource/doc/conf_interval.md VMAF confidence interval page] for more details.
:::* topk
:::Default: False.
:::: Ratio of pixels for the spatial pooling computation.
:::: Must be between 0.0001 and 1.0.
:::: Default: 0.6.
:::* tvi_threshold
:::: Visibilty threshold for luminance ΔL < tvi_threshold*L_mean for BT.1886.
:::: Must be between 0.0001 and 1.0.
:::: Default: 0.019.
::: Format: <code>option_name=value</code>.
::: If more than one option is specified, the options must be separated by space.
::: Usage example: <code>cambi_opt="windows_size=120 enc_width=1280 enc_height=720"</code>.
<br>
<br>


==Examples==
==Examples==
Comparing a high quality clip vs an encoded clip:  
Comparing a high quality clip vs an encoded clip:
  VMAF(HQ_original, HQ_encoded, model=0, ssim=false, ms_ssim=false, pool=1, ci=false)
  VMAF(HQ_original, HQ_encoded, model=0)
 
<br>
Comparing a high quality clip vs an encoded clip with MS-SSIM metrics only:
VMAF(HQ_original, HQ_encoded, feature=3)
<br>
<br>


== Changelog ==
== Changelog ==
  Version      Date            Changes<br>
  Version      Date            Changes<br>
v2.1.0      2021/11/14      - Added parameter cambi_opt
                                                  - Removed model default value<br>
v2.0.2      2021/10/20      - Fixed feature parameter
                                                  - Updated vmaf lib to 2.3.0
                                                  - Added feature CAMBI<br>
v2.0.1      2021/10/02      - Fixed crashing when unsupported color formats are used
                                                  - Updated libvmaf to 2.2.1<br>
v2.0.0      2021/07/10      - Updated to libvmaf 2.x<br>
  v1.0.0      2020/11/14      - Initial release
  v1.0.0      2020/11/14      - Initial release
                              - AviSynth+: self-registers as [[MT_SERIALIZED]]  
                                                  - AviSynth+: self-registers as [[MT_SERIALIZED]]
<br>
<br>


Revision as of 00:11, 13 January 2022

Abstract
Author Asd-g
Version v2.1.0
Download VMAF
Category Debug filter
License MIT
Discussion

Description

VMAF is a perceptual video quality assessment algorithm developed by Netflix. Refer to the FAQ page for frequently asked questions of VMAF.

This is a port of the VapourSynth plugin VMAF.

vmaf is used.

Requirements



Syntax and Parameters

VMAF (clip reference, clip distorted, string log_path, int "log_format", int[] "model", int[] "feature", string "cambi_opt")


reference   =
distorted   =
Clips to calculate VMAF score. Must be in YUV 8..16-bit planar format.
Must be in YUV 8..16-bit planar format with minimum three planes.


string  log_path =
Sets the path of the log file.


int  log_format = 0
Sets the format of the log file.
  • 0 : xml.
  • 1 : json.
  • 2 : csv.


int[]  model =
Sets which model to use. Refer to this, this and this page for more details.
  • 0 : vmaf_v0.6.1
  • 1 : vmaf_v0.6.1neg (NEG mode)
  • 2 : vmaf_b_v0.6.3 (Confidence Interval)
  • 3 : vmaf_4k_v0.6.1


int[]  feature =
  • 0 : PSNR
  • 1 : PSNR-HVS
  • 2 : SSIM
  • 3 : MS-SSIM
  • 4 : CIEDE2000
  • 5 : CAMBI


string  cambi_opt =
  • enc_width, enc_height
Encoding/processing resolution to compute the banding score, useful in cases where scaling was applied to the input prior to the computation of metrics.
enc_width must be between 320 and 7680.
enc_height must be between 200 and 4320.
Default: Same as input image.
  • window_size
Window size to compute CAMBI.
Must be between 15 and 127.
Default: 63 (corresponds to ~1 degree at 4K resolution and 1.5H).
  • topk
Ratio of pixels for the spatial pooling computation.
Must be between 0.0001 and 1.0.
Default: 0.6.
  • tvi_threshold
Visibilty threshold for luminance ΔL < tvi_threshold*L_mean for BT.1886.
Must be between 0.0001 and 1.0.
Default: 0.019.
Format: option_name=value.
If more than one option is specified, the options must be separated by space.
Usage example: cambi_opt="windows_size=120 enc_width=1280 enc_height=720".


Examples

Comparing a high quality clip vs an encoded clip: 

VMAF(HQ_original, HQ_encoded, model=0)


Comparing a high quality clip vs an encoded clip with MS-SSIM metrics only: 

VMAF(HQ_original, HQ_encoded, feature=3)


Changelog

Version      Date            Changes

v2.1.0       2021/11/14      - Added parameter cambi_opt
                                                 - Removed model default value

v2.0.2       2021/10/20      - Fixed feature parameter
                                                 - Updated vmaf lib to 2.3.0
                                                 - Added feature CAMBI

v2.0.1       2021/10/02      - Fixed crashing when unsupported color formats are used
                                                 - Updated libvmaf to 2.2.1

v2.0.0       2021/07/10      - Updated to libvmaf 2.x

v1.0.0       2020/11/14      - Initial release
                                                 - AviSynth+: self-registers as MT_SERIALIZED


  • GitHub - Source code repository.



Back to External Filters ←

Retrieved from "http://www.avisynth.nl/index.php?title=VMAF&oldid=12536"