VMAF - Revision history

Asd: VMAF 2.1.2

2023-05-18T07:35:09Z

VMAF 2.1.2

Reel.Deal: /* Description */ fix broken link

2022-05-17T12:38:09Z

‎Description: fix broken link

Asd: Update the version

2022-05-16T01:13:48Z

Update the version

Asd: Update to the latest version

2022-01-12T22:11:33Z

Update to the latest version

Reel.Deal: VMAF v1.0.0

2020-11-15T08:47:45Z

VMAF v1.0.0

New page

{{FilterCat6|External_filters|Plugins|Plugins_x64|Other_filters|Debugging/Diagnostic_filters|Deep_color_tools}}
{{Filter3
| 1={{Author/Asd-g}}
| 2=v1.0.0
| 3=[https://github.com/Asd-g/AviSynth-VMAF/releases/ VMAF-1.0.0.7z]
| 4=Debug filter
| 5=[https://github.com/Asd-g/AviSynth-VMAF/blob/main/LICENSE MIT]
| 6=}}

== Description ==
[[VMAF]] is a perceptual video quality assessment algorithm developed by Netflix. Refer to the [https://github.com/Netflix/vmaf/blob/master/FAQ.md FAQ] page for frequently asked questions of 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.
 
 
== Requirements ==
* [x86] [[AviSynth+]] or [https://sourceforge.net/projects/avisynth2/ AviSynth 2.6]
* [x64] [[AviSynth+]]
* Supported color formats: [[Y8]], [[YV12]], [[YV16]], [[YV24]], [[YV411]]
**AviSynth+: all [[planar]] Y and YUV formats (8/10/12/14/16bit) are supported.
 
'''NOTE:'''The folder <code>model</code> must be located in the same folder as <code>VMAF.dll</code>.
 
 
== [[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")}}
 
::{{Par2| |clip| }}
::{{Par2| |clip| }}
::: 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).
 
::{{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.
 
::{{Par2|log_path|string|}}
:::Sets the path of the log file.
:::Default: None.
 
::{{Par2|log_fmt|int|0}}
:::Sets the format of the log file.
:::*0: xml.
:::*1: json.
:::*2: csv.
:::Default: 0.
 
::{{Par2|ssim|bool|false}}
:::Whether to also calculate SSIM score.
:::Default: False.
 
::{{Par2|ms_ssim|bool|false}}
:::Whether to also calculate MS-SSIM score.
:::Default: False.
 
::{{Par2|pool|int|1}}
:::Sets the method to pool the per-frame scores.
:::*0: Mean.
:::*1: Harmonic mean.
:::*2: Min.
:::Default: 1.
 
::{{Par2|ci|bool|false}}
:::Whether to enable confidence interval.
:::True: It uses vmaf_b_v0.6.3 for model=0 and vmaf_4k_rb_v0.6.2 for model=1.
:::Refer to the [https://github.com/Netflix/vmaf/blob/v1.3.15/resource/doc/conf_interval.md VMAF confidence interval page] for more details.
:::Default: False.
 

==Examples==
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)

 

== Changelog ==
Version Date Changes 
v1.0.0 2020/11/14 - Initial release
- AviSynth+: self-registers as [[MT_SERIALIZED]]
 

==External Links ==
*[https://github.com/Asd-g/AviSynth-VMAF GitHub] - Source code repository.
 
 
-----------------------------------------------
'''Back to [[External_filters#Debugging.2FDiagnostic_Filters|External Filters]] ←'''

@@ Line 2: / Line 2: @@
 {{Filter3
 | 1={{Author/Asd-g}}
-| 2=v2.1.1
+| 2=v2.1.2
 | 3=[https://github.com/Asd-g/AviSynth-VMAF/releases/ VMAF]
 | 4=Debug filter
@@ Line 99: / Line 99: @@
 == Changelog ==
   Version      Date            Changes<br>
   v2.1.1       2022/04/18      - Added `cambi_opt` options - `max_log_contrast`, `enc_bitdepth`, `eotf`
                                - Added function `VMAF2`

@@ Line 2: / Line 2: @@
 {{Filter3
 | 1={{Author/Asd-g}}
-| 2=v2.1.0
+| 2=v2.1.1
 | 3=[https://github.com/Asd-g/AviSynth-VMAF/releases/ VMAF]
 | 4=Debug filter
@@ Line 20: / Line 20: @@
 * [x64] [[AviSynth+]]
 * 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 (8/10bit) are supported.
 <br>
 <br>
 == [[Script variables|Syntax and Parameters]] ==
 :{{Template:FuncDef|VMAF (clip reference, clip distorted, string log_path, int "log_format", int[] "model", int[] "feature", string "cambi_opt")}}
 <br>
 ::{{Par2| |reference| }}
 ::{{Par2| |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.
+::: <code>distorted</code> must be specified when feature != 5. (VMAF2 only)
 <br>
 ::{{Par2|log_path|string|}}
 :::Sets the path of the log file.
 <br>
 ::{{Par2|log_format|int|0}}
@@ Line 39: / Line 42: @@
 :::*1 : json.
 :::*2 : csv.
 <br>
 ::{{Par2|model|int[]|}}
@@ Line 46: / Line 50: @@
 :::*2 : vmaf_b_v0.6.3 (Confidence Interval)
 :::*3 : vmaf_4k_v0.6.1
 <br>
 ::{{Par2|feature|int[]|}}
@@ Line 76: / Line 81: @@
 ::: 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>
@@ Line 84: / Line 91: @@
 Comparing a high quality clip vs an encoded clip with MS-SSIM metrics only:
   VMAF(HQ_original, HQ_encoded, feature=3)
 <br>
 == Changelog ==
   Version      Date            Changes<br>
   v2.1.0       2021/11/14      - Added parameter cambi_opt
-                                                  - Removed model default value<br>
+                              - Removed model default value<br>
   v2.0.2       2021/10/20      - Fixed feature parameter
-                                                  - Updated vmaf lib to 2.3.0
+                              - Updated vmaf lib to 2.3.0
-                                                  - Added feature CAMBI<br>
+                              - 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>
+                              - 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
-                                                  - AviSynth+: self-registers as [[MT_SERIALIZED]]
+                              - AviSynth+: self-registers as [[MT_SERIALIZED]]
 <br>

@@ Line 9: / Line 9: @@
 == Description ==
-[[VMAF]] is a perceptual video quality assessment algorithm developed by Netflix. Refer to the [https://github.com/Netflix/vmaf/blob/master/FAQ.md FAQ] page for frequently asked questions of VMAF.
+[[VMAF]] is a perceptual video quality assessment algorithm developed by Netflix. Refer to the [https://github.com/Netflix/vmaf/blob/master/resource/doc/faq.md FAQ] page for frequently asked questions of VMAF.
 This is [https://github.com/HomeOfVapourSynthEvolution/VapourSynth-VMAF a port of the VapourSynth plugin VMAF.]
@@ Line 16: / Line 16: @@
 <br>
 <br>
 == Requirements ==
 * [x86] [[AviSynth+]] or [https://sourceforge.net/projects/avisynth2/ AviSynth 2.6]

@@ Line 2: / Line 2: @@
 {{Filter3
 | 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
 | 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.]
-[https://github.com/Netflix/vmaf/tree/v1.3.15 vmaf] is used.
+[https://github.com/Netflix/vmaf vmaf] is used.
 <br>
 <br>
@@ Line 21: / Line 21: @@
 * Supported color formats: [[Y8]], [[YV12]], [[YV16]], [[YV24]], [[YV411]]
 **AviSynth+: all [[planar]] Y and YUV formats (8/10/12/14/16bit) are supported.
 <br>
 <br>
 == [[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>
-::{{Par2| |clip| }}
+::{{Par2| |reference| }}
-::{{Par2| |clip| }}
+::{{Par2| |distorted| }}
 ::: 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>
 ::{{Par2|log_path|string|}}
 :::Sets the path of the log file.
 <br>
-::{{Par2|log_fmt|int|0}}
+::{{Par2|log_format|int|0}}
 :::Sets the format of the log file.
-:::*0: xml.
+:::*0 : xml.
-:::*1: json.
+:::*1 : json.
-:::*2: csv.
+:::*2 : csv.
-:::Default: 0.
 <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
 <br>
-::{{Par2|ms_ssim|bool|false}}
+::{{Par2|feature|int[]|}}
-:::Whether to also calculate MS-SSIM score.
+:::*0 : PSNR
-:::Default: False.
+:::*1 : PSNR-HVS
 <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.
 <br>
 ==Examples==
 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>
 <br>
 == Changelog ==
   Version      Date            Changes<br>
   v1.0.0       2020/11/14      - Initial release
-                              - AviSynth+: self-registers as [[MT_SERIALIZED]]
+                                                  - AviSynth+: self-registers as [[MT_SERIALIZED]]
 <br>