---
title: Visual Information Fidelity (VIF)
description: Compute Pixel Based Visual Information Fidelity (VIF).
canonical: >-
  https://lightning.ai/docs/torchmetrics/stable/image/visual_information_fidelity
---
# Visual Information Fidelity (VIF) {#visual-information-fidelity-vif}

## Module Interface {#module-interface}

### `class torchmetrics.image.VisualInformationFidelity(sigma_n_sq=2.0, reduction='mean', **kwargs)` {#torchmetrics.image.VisualInformationFidelity}

[\[source\]](https://github.com/Lightning-AI/torchmetrics/blob/v1.9.0/src/torchmetrics/image/vif.py#L25-L99)

Compute Pixel Based Visual Information Fidelity ([VIF](https://ieeexplore.ieee.org/abstract/document/1576816)).

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)")): Predictions from model of shape `(N,C,H,W)` with H,W ≥ 41
    
*   `target` ([`Tensor`](https://docs.pytorch.org/docs/stable/tensors.html#torch.Tensor "(in PyTorch v2.15)")): Ground truth values of shape `(N,C,H,W)` with H,W ≥ 41
    

As output of forward and compute the metric returns the following output

*   `vif-p` ([`Tensor`](https://docs.pytorch.org/docs/stable/tensors.html#torch.Tensor "(in PyTorch v2.15)")):
    
    *   If `reduction='mean'` (default), returns a Tensor mean VIF score.
        
    *   If `reduction='none'`, returns a tensor of shape `(N,)` with VIF values per sample.
        
    

Parameters:

*   **sigma\_n\_sq** ([`float`](https://docs.python.org/3/builtins/functions.html#float "(in Python v3.15)")) – variance of the visual noise
    
*   **reduction** ([`Literal`](https://docs.python.org/3/library/typing.html#typing.Literal "(in Python v3.15)")\[`'mean'`, `'none'`\]) –
    
    The reduction method for aggregating scores.
    
    *   `'mean'`: return the average VIF across the batch.
        
    *   `'none'`: return a VIF score for each sample in the batch.
        
    
*   **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.
    

Example

```python
>>> from torch import randn
>>> from torchmetrics.image import VisualInformationFidelity
>>> preds = randn([32, 3, 41, 41], generator=torch.Generator().manual_seed(42))
>>> target = randn([32, 3, 41, 41], generator=torch.Generator().manual_seed(43))
>>> vif_mean = VisualInformationFidelity(reduction='mean')
>>> vif_mean(preds, target)
tensor(0.0032)
>>> vif_none = VisualInformationFidelity(reduction='none')
>>> vif_none(preds, target)
tensor([0.0040, 0.0049, 0.0017, 0.0039, 0.0041, 0.0043, 0.0030, 0.0028, 0.0012,
        0.0067, 0.0010, 0.0014, 0.0030, 0.0048, 0.0050, 0.0038, 0.0037, 0.0025,
        0.0041, 0.0019, 0.0007, 0.0034, 0.0037, 0.0016, 0.0026, 0.0021, 0.0038,
        0.0033, 0.0031, 0.0020, 0.0036, 0.0057])
```

## Functional Interface {#functional-interface}

### `torchmetrics.functional.image.visual_information_fidelity(preds, target, sigma_n_sq=2.0, reduction='mean')` {#torchmetrics.functional.image.visual_information_fidelity}

[\[source\]](https://github.com/Lightning-AI/torchmetrics/blob/v1.9.0/src/torchmetrics/functional/image/vif.py#L89-L154)

Compute Pixel-Based Visual Information Fidelity (VIF-P).

VIF is a full-reference metric that measures the amount of visual information preserved in a distorted image compared to the reference image.

Parameters:

*   **preds** ([`Tensor`](https://docs.pytorch.org/docs/stable/tensors.html#torch.Tensor "(in PyTorch v2.15)")) – Predicted images of shape (N, C, H, W). Height and width must be at least 41.
    
*   **target** ([`Tensor`](https://docs.pytorch.org/docs/stable/tensors.html#torch.Tensor "(in PyTorch v2.15)")) – Ground truth images of shape (N, C, H, W). Must match preds in shape.
    
*   **sigma\_n\_sq** ([`float`](https://docs.python.org/3/builtins/functions.html#float "(in Python v3.15)")) – Variance of the visual noise. Default: 2.0.
    
*   **reduction** ([`Literal`](https://docs.python.org/3/library/typing.html#typing.Literal "(in Python v3.15)")\[`'mean'`, `'none'`\]) – Method for reducing the metric across the batch. - “mean”: Return a tensor average over the batch. - “none”: Return a VIF score for each sample as a 1D tensor of shape (N,).
    

Returns:

VIF score(s). The shape depends on the reduction argument:

*   If `reduction="mean"`, returns a scalar tensor.
    
*   If `reduction="none"`, returns a tensor of shape `(N,)`.
    

Return type:

[torch.Tensor](https://docs.pytorch.org/docs/stable/tensors.html#torch.Tensor "(in PyTorch v2.15)")

Raises:

*   [**ValueError**](https://docs.python.org/3/builtins/exceptions.html#ValueError "(in Python v3.15)") – If input dimensions are smaller than `41x41`.
    
*   [**ValueError**](https://docs.python.org/3/builtins/exceptions.html#ValueError "(in Python v3.15)") – If `preds` and `target` shapes don’t match.
    
*   [**ValueError**](https://docs.python.org/3/builtins/exceptions.html#ValueError "(in Python v3.15)") – If `reduction` is not `"mean"` or `"none"`.
    

Example

```python
>>> from torchmetrics.functional.image import visual_information_fidelity
>>> preds = torch.randn(4, 3, 41, 41, generator=torch.Generator().manual_seed(42))
>>> target = torch.randn(4, 3, 41, 41, generator=torch.Generator().manual_seed(43))
>>> visual_information_fidelity(preds, target, reduction="none")
tensor([0.0040, 0.0049, 0.0017, 0.0039])
```

---

**Navigation**

- Parent: [Image](/docs/torchmetrics/1.9.0/image.md)