---
title: Video Multi-Method Assessment Fusion (VMAF)
description: Calculates Video Multi-Method Assessment Fusion (VMAF) metric.
canonical: 'https://lightning.ai/docs/torchmetrics/stable/video/vmaf'
---
# Video Multi-Method Assessment Fusion (VMAF) {#video-multi-method-assessment-fusion-vmaf}

## Module Interface {#module-interface}

### `class torchmetrics.video.vmaf.VideoMultiMethodAssessmentFusion(features=False, **kwargs)` {#class-torchmetrics-video-vmaf-videomultimethodassessmentfusion-features-false-kwargs}

[\[source\]](https://github.com/Lightning-AI/torchmetrics/blob/v1.9.0/src/torchmetrics/video/vmaf.py#L27-L187)

Calculates Video Multi-Method Assessment Fusion (VMAF) metric.

VMAF is a full-reference video quality assessment algorithm that combines multiple quality assessment features such as detail loss, motion, and contrast using a machine learning model to predict human perception of video quality more accurately than traditional metrics like PSNR or SSIM.

The metric works by:

1.  Converting input videos to luma component (grayscale)
    
2.  Computing multiple elementary features: - Additive Detail Measure (ADM): Evaluates detail preservation at different scales - Visual Information Fidelity (VIF): Measures preservation of visual information across frequency bands - Motion: Quantifies the amount of motion in the video
    
3.  Combining these features using a trained SVM model to predict quality
    

Note

This implementation requires you to have vmaf-torch installed: [https://github.com/alvitrioliks/VMAF-torch](https://github.com/alvitrioliks/VMAF-torch). Install either by cloning the repository and running `pip install .` or with `pip install torchmetrics[video]`.

As input to `forward` and `update` the metric accepts the following input:

*   `preds` ([`Tensor`](https://docs.pytorch.org/docs/stable/tensors.html#torch.Tensor "(in PyTorch v2.15)")): Video tensor of shape `(batch, channels, frames, height, width)`. Expected to be in RGB format with values in range \[0, 1\].
    
*   `target` ([`Tensor`](https://docs.pytorch.org/docs/stable/tensors.html#torch.Tensor "(in PyTorch v2.15)")): Video tensor of shape `(batch, channels, frames, height, width)`. Expected to be in RGB format with values in range \[0, 1\].
    

As output of `forward` and `compute` the metric returns the following output `vmaf` ([`Tensor`](https://docs.pytorch.org/docs/stable/tensors.html#torch.Tensor "(in PyTorch v2.15)")):

*   If `features` is False, returns a tensor with shape (batch, frame) of VMAF score for each frame in each video. Higher scores indicate better quality, with typical values ranging from 0 to 100.
    
*   If `features` is True, returns a dictionary where each value is a (batch, frame) tensor of the corresponding feature. The keys are:
    
    *   ‘integer\_motion2’: Integer motion feature
        
    *   ‘integer\_motion’: Integer motion feature
        
    *   ‘integer\_adm2’: Integer ADM feature
        
    *   ‘integer\_adm\_scale0’: Integer ADM feature at scale 0
        
    *   ‘integer\_adm\_scale1’: Integer ADM feature at scale 1
        
    *   ‘integer\_adm\_scale2’: Integer ADM feature at scale 2
        
    *   ‘integer\_adm\_scale3’: Integer ADM feature at scale 3
        
    *   ‘integer\_vif\_scale0’: Integer VIF feature at scale 0
        
    *   ‘integer\_vif\_scale1’: Integer VIF feature at scale 1
        
    *   ‘integer\_vif\_scale2’: Integer VIF feature at scale 2
        
    *   ‘integer\_vif\_scale3’: Integer VIF feature at scale 3
        
    *   ‘vmaf’: VMAF score for each frame in each video
        

Parameters:

*   **features** ([`bool`](https://docs.python.org/3/builtins/functions.html#bool "(in Python v3.15)")) – If True, all the elementary features (ADM, VIF, motion) are returned along with the VMAF score in a dictionary. This corresponds to the output you would get from the VMAF command line tool with the `--csv` option enabled. If False, only the VMAF score is returned as a tensor.
    
*   **kwargs** ([`Any`](https://docs.python.org/3/library/typing.html#typing.Any "(in Python v3.15)")) – Additional keyword arguments, see [Advanced metric settings](/docs/torchmetrics/1.9.0/user-guide/overview.md#metric-kwargs) for more info.
    

Raises:

*   [**RuntimeError**](https://docs.python.org/3/builtins/exceptions.html#RuntimeError "(in Python v3.15)") – If vmaf-torch is not installed.
    
*   [**ValueError**](https://docs.python.org/3/builtins/exceptions.html#ValueError "(in Python v3.15)") – If `features` is not a boolean.
    

Example

```python
>>> import torch
>>> from torchmetrics.video import VideoMultiMethodAssessmentFusion
>>> # 2 videos, 3 channels, 10 frames, 32x32 resolution
>>> preds = torch.rand(2, 3, 10, 32, 32, generator=torch.manual_seed(42))
>>> target = torch.rand(2, 3, 10, 32, 32, generator=torch.manual_seed(43))
>>> vmaf = VideoMultiMethodAssessmentFusion()
>>> torch.round(vmaf(preds, target), decimals=2)
tensor([[ 9.9900, 15.9000, 14.2600, 16.6100, 15.9100, 14.3000, 13.5800, 13.4900, 15.4700, 20.2800],
        [ 6.2500, 11.3000, 17.3000, 11.4600, 19.0600, 14.9300, 14.0500, 14.4100, 12.4700, 14.8200]])
>>> vmaf = VideoMultiMethodAssessmentFusion(features=True)
>>> vmaf_dict = vmaf(preds, target)
>>> vmaf_dict['vmaf'].round(decimals=2)
tensor([[ 9.9900, 15.9000, 14.2600, 16.6100, 15.9100, 14.3000, 13.5800, 13.4900, 15.4700, 20.2800],
        [ 6.2500, 11.3000, 17.3000, 11.4600, 19.0600, 14.9300, 14.0500, 14.4100, 12.4700, 14.8200]])
>>> vmaf_dict['integer_adm2'].round(decimals=2)
tensor([[0.4500, 0.4500, 0.3600, 0.4700, 0.4300, 0.3600, 0.3900, 0.4100, 0.3700, 0.4700],
        [0.4200, 0.3900, 0.4400, 0.3700, 0.4500, 0.3900, 0.3800, 0.4800, 0.3900, 0.3900]])
```

#### `compute()` {#compute}

[\[source\]](https://github.com/Lightning-AI/torchmetrics/blob/v1.9.0/src/torchmetrics/video/vmaf.py#L170-L187)

Compute final VMAF score.

Return type:

`Union`\[[`Tensor`](https://docs.pytorch.org/docs/stable/tensors.html#torch.Tensor "(in PyTorch v2.15)"), [`Dict`](https://docs.python.org/3/library/typing.html#typing.Dict "(in Python v3.15)")\[[`str`](https://docs.python.org/3/builtins/stdtypes.html#str "(in Python v3.15)"), [`Tensor`](https://docs.pytorch.org/docs/stable/tensors.html#torch.Tensor "(in PyTorch v2.15)")\]\]

#### `update(preds, target)` {#update-preds-target}

[\[source\]](https://github.com/Lightning-AI/torchmetrics/blob/v1.9.0/src/torchmetrics/video/vmaf.py#L151-L168)

Update state with predictions and targets.

Return type:

[`None`](https://docs.python.org/3/builtins/constants.html#None "(in Python v3.15)")

## Functional Interface {#functional-interface}

### `torchmetrics.functional.video.vmaf.video_multi_method_assessment_fusion(preds, target, features=False)` {#torchmetrics-functional-video-vmaf-video-multi-method-assessment-fusion-preds-target-features-false}

[\[source\]](https://github.com/Lightning-AI/torchmetrics/blob/v1.9.0/src/torchmetrics/functional/video/vmaf.py#L39-L142)

Calculates Video Multi-Method Assessment Fusion (VMAF) metric.

VMAF is a full-reference video quality assessment algorithm that combines multiple quality assessment features such as detail loss, motion, and contrast using a machine learning model to predict human perception of video quality more accurately than traditional metrics like PSNR or SSIM.

The metric works by:

1.  Converting input videos to luma component (grayscale)
    
2.  Computing multiple elementary features: - Additive Detail Measure (ADM): Evaluates detail preservation at different scales - Visual Information Fidelity (VIF): Measures preservation of visual information across frequency bands - Motion: Quantifies the amount of motion in the video
    
3.  Combining these features using a trained SVM model to predict quality
    

Note

This implementation requires you to have vmaf-torch installed: [https://github.com/alvitrioliks/VMAF-torch](https://github.com/alvitrioliks/VMAF-torch). Install either by cloning the repository and running pip install . or with pip install torchmetrics\[video\].

Parameters:

*   **preds** ([`Tensor`](https://docs.pytorch.org/docs/stable/tensors.html#torch.Tensor "(in PyTorch v2.15)")) – Video tensor of shape (batch, channels, frames, height, width). Expected to be in RGB format with values in range \[0, 1\].
    
*   **target** ([`Tensor`](https://docs.pytorch.org/docs/stable/tensors.html#torch.Tensor "(in PyTorch v2.15)")) – Video tensor of shape (batch, channels, frames, height, width). Expected to be in RGB format with values in range \[0, 1\].
    
*   **features** ([`bool`](https://docs.python.org/3/builtins/functions.html#bool "(in Python v3.15)")) – If True, all the elementary features (ADM, VIF, motion) are returned along with the VMAF score in a dictionary. This corresponds to the output you would get from the VMAF command line tool with the –csv option enabled. If False, only the VMAF score is returned as a tensor.
    

Return type:

`Union`\[[`Tensor`](https://docs.pytorch.org/docs/stable/tensors.html#torch.Tensor "(in PyTorch v2.15)"), [`Dict`](https://docs.python.org/3/library/typing.html#typing.Dict "(in Python v3.15)")\[[`str`](https://docs.python.org/3/builtins/stdtypes.html#str "(in Python v3.15)"), [`Tensor`](https://docs.pytorch.org/docs/stable/tensors.html#torch.Tensor "(in PyTorch v2.15)")\]\]

Returns:

*   If features is False, returns a tensor with shape (batch, frame) of VMAF score for each frame in each video. Higher scores indicate better quality, with typical values ranging from 0 to 100.
    
*   If features is True, returns a dictionary where each value is a (batch, frame) tensor of the corresponding feature. The keys are:
    
    *   ’integer\_motion2’: Integer motion feature
        
    *   ’integer\_motion’: Integer motion feature
        
    *   ’integer\_adm2’: Integer ADM feature
        
    *   ’integer\_adm\_scale0’: Integer ADM feature at scale 0
        
    *   ’integer\_adm\_scale1’: Integer ADM feature at scale 1
        
    *   ’integer\_adm\_scale2’: Integer ADM feature at scale 2
        
    *   ’integer\_adm\_scale3’: Integer ADM feature at scale 3
        
    *   ’integer\_vif\_scale0’: Integer VIF feature at scale 0
        
    *   ’integer\_vif\_scale1’: Integer VIF feature at scale 1
        
    *   ’integer\_vif\_scale2’: Integer VIF feature at scale 2
        
    *   ’integer\_vif\_scale3’: Integer VIF feature at scale 3
        
    *   ’vmaf’: VMAF score for each frame in each video
        

Example

```python
>>> import torch
>>> from torchmetrics.functional.video import video_multi_method_assessment_fusion
>>> # 2 videos, 3 channels, 10 frames, 32x32 resolution
>>> preds = torch.rand(2, 3, 10, 32, 32, generator=torch.manual_seed(42))
>>> target = torch.rand(2, 3, 10, 32, 32, generator=torch.manual_seed(43))
>>> vmaf_score = video_multi_method_assessment_fusion(preds, target)
>>> torch.round(vmaf_score, decimals=2)
tensor([[ 9.9900, 15.9000, 14.2600, 16.6100, 15.9100, 14.3000, 13.5800, 13.4900, 15.4700, 20.2800],
        [ 6.2500, 11.3000, 17.3000, 11.4600, 19.0600, 14.9300, 14.0500, 14.4100, 12.4700, 14.8200]])
>>> vmaf_dict = video_multi_method_assessment_fusion(preds, target, features=True)
>>> # show a couple of features, more features are available
>>> vmaf_dict['vmaf'].round(decimals=2)
tensor([[ 9.9900, 15.9000, 14.2600, 16.6100, 15.9100, 14.3000, 13.5800, 13.4900, 15.4700, 20.2800],
        [ 6.2500, 11.3000, 17.3000, 11.4600, 19.0600, 14.9300, 14.0500, 14.4100, 12.4700, 14.8200]])
>>> vmaf_dict['integer_adm2'].round(decimals=2)
tensor([[0.4500, 0.4500, 0.3600, 0.4700, 0.4300, 0.3600, 0.3900, 0.4100, 0.3700, 0.4700],
        [0.4200, 0.3900, 0.4400, 0.3700, 0.4500, 0.3900, 0.3800, 0.4800, 0.3900, 0.3900]])
```

---

**Navigation**

- Parent: [Video](/docs/torchmetrics/1.9.0/video.md)