Table of Contents

Class VRT<T>

Namespace
AiDotNet.Video.Restoration
Assembly
AiDotNet.dll

VRT: A Video Restoration Transformer for video super-resolution, deblurring, and denoising.

public class VRT<T> : NeuralNetworkBase<T>, INeuralNetworkModel<T>, INeuralNetwork<T>, IFullModel<T, Tensor<T>, Tensor<T>>, IModel<Tensor<T>, Tensor<T>, ModelMetadata<T>>, IModelSerializer, ICheckpointableModel, IParameterizable<T, Tensor<T>, Tensor<T>>, IFeatureAware, IFeatureImportance<T>, ICloneable<IFullModel<T, Tensor<T>, Tensor<T>>>, IGradientComputable<T, Tensor<T>, Tensor<T>>, IJitCompilable<T>, IInterpretableModel<T>, IInputGradientComputable<T>, IDisposable

Type Parameters

T

The numeric type used for calculations (typically float or double).

Inheritance
VRT<T>
Implements
IFullModel<T, Tensor<T>, Tensor<T>>
IModel<Tensor<T>, Tensor<T>, ModelMetadata<T>>
IParameterizable<T, Tensor<T>, Tensor<T>>
ICloneable<IFullModel<T, Tensor<T>, Tensor<T>>>
IGradientComputable<T, Tensor<T>, Tensor<T>>
Inherited Members
Extension Methods

Remarks

VRT (Video Restoration Transformer) is a powerful architecture for video restoration tasks: - Video super-resolution (increasing video resolution) - Video deblurring (removing motion blur) - Video denoising (removing noise from videos)

For Beginners: VRT improves video quality by analyzing multiple frames together. Unlike image restoration that processes one frame at a time, VRT uses temporal information to produce better, more consistent results.

Example usage (native mode for training):

var arch = new NeuralNetworkArchitecture<double>(
    inputType: InputType.ThreeDimensional,
    inputHeight: 64, inputWidth: 64, inputDepth: 3);
var model = new VRT<double>(arch, scaleFactor: 4);
model.Train(lowResFrames, highResFrames);
var restoredFrame = model.Restore(lowResFrame);

Example usage (ONNX mode for inference only):

var arch = new NeuralNetworkArchitecture<double>(
    inputType: InputType.ThreeDimensional,
    inputHeight: 64, inputWidth: 64, inputDepth: 3);
var model = new VRT<double>(arch, "vrt.onnx");
var restoredFrame = model.Restore(lowResFrame);

Reference: "VRT: A Video Restoration Transformer" https://arxiv.org/abs/2201.12288

Constructors

VRT(NeuralNetworkArchitecture<T>, IGradientBasedOptimizer<T, Tensor<T>, Tensor<T>>?, ILossFunction<T>?, int, int, int, int)

Creates a VRT model using native layers for training and inference.

public VRT(NeuralNetworkArchitecture<T> architecture, IGradientBasedOptimizer<T, Tensor<T>, Tensor<T>>? optimizer = null, ILossFunction<T>? lossFunction = null, int embedDim = 120, int numFrames = 6, int numBlocks = 8, int scaleFactor = 4)

Parameters

architecture NeuralNetworkArchitecture<T>

Architecture for the video restoration network.

optimizer IGradientBasedOptimizer<T, Tensor<T>, Tensor<T>>

Optional optimizer for training. Default: Adam.

lossFunction ILossFunction<T>

Optional loss function. Default: MSE.

embedDim int

Embedding dimension (default: 120).

numFrames int

Number of frames to process together (default: 6).

numBlocks int

Number of transformer blocks (default: 8).

scaleFactor int

Upscaling factor (default: 4).

Remarks

For Beginners: Create a trainable VRT model: 

var arch = new NeuralNetworkArchitecture<double>(
    inputType: InputType.ThreeDimensional,
    inputHeight: 64, inputWidth: 64, inputDepth: 3);
var model = new VRT<double>(arch, scaleFactor: 4);

VRT(NeuralNetworkArchitecture<T>, string, int)

Creates a VRT model using a pretrained ONNX model for inference.

public VRT(NeuralNetworkArchitecture<T> architecture, string onnxModelPath, int scaleFactor = 4)

Parameters

architecture NeuralNetworkArchitecture<T>

The neural network architecture configuration.

onnxModelPath string

Path to the pretrained ONNX model.

scaleFactor int

Scale factor of the model (default: 4).

Remarks

For Beginners: Use this constructor when you have a pretrained model in ONNX format. Training is not supported in ONNX mode. 

var arch = new NeuralNetworkArchitecture<double>(
    inputType: InputType.ThreeDimensional,
    inputHeight: 64, inputWidth: 64, inputDepth: 3);
var model = new VRT<double>(arch, "vrt_sr_x4.onnx");
var restoredFrame = model.Restore(lowResFrame);

Exceptions

FileNotFoundException

Thrown if the ONNX model file is not found.

Properties

SupportsTraining

Gets whether training is supported (only in native mode).

public override bool SupportsTraining { get; }

Property Value

bool

Methods

CreateNewInstance()

Creates a new instance of the same type as this neural network.

protected override IFullModel<T, Tensor<T>, Tensor<T>> CreateNewInstance()

Returns

IFullModel<T, Tensor<T>, Tensor<T>>

A new instance of the same neural network type.

Remarks

For Beginners: This creates a blank version of the same type of neural network.

It's used internally by methods like DeepCopy and Clone to create the right type of network before copying the data into it.

Deblur(Tensor<T>)

Performs video deblurring.

public Tensor<T> Deblur(Tensor<T> blurryFrames)

Parameters

blurryFrames Tensor<T>

Blurry video frames.

Returns

Tensor<T>

Deblurred video frames.

Denoise(Tensor<T>)

Performs video denoising.

public Tensor<T> Denoise(Tensor<T> noisyFrames)

Parameters

noisyFrames Tensor<T>

Noisy video frames.

Returns

Tensor<T>

Denoised video frames.

DeserializeNetworkSpecificData(BinaryReader)

Deserializes network-specific data that was not covered by the general deserialization process.

protected override void DeserializeNetworkSpecificData(BinaryReader reader)

Parameters

reader BinaryReader

The BinaryReader to read the data from.

Remarks

This method is called at the end of the general deserialization process to allow derived classes to read any additional data specific to their implementation.

For Beginners: Continuing the suitcase analogy, this is like unpacking that special compartment. After the main deserialization method has unpacked the common items (layers, parameters), this method allows each specific type of neural network to unpack its own unique items that were stored during serialization.

GetModelMetadata()

Gets the metadata for this neural network model.

public override ModelMetadata<T> GetModelMetadata()

Returns

ModelMetadata<T>

A ModelMetaData object containing information about the model.

InitializeLayers()

Initializes the layers of the neural network based on the architecture.

protected override void InitializeLayers()

Remarks

For Beginners: This method sets up all the layers in your neural network according to the architecture you've defined. It's like assembling the parts of your network before you can use it.

Predict(Tensor<T>)

Makes a prediction using the neural network.

public override Tensor<T> Predict(Tensor<T> input)

Parameters

input Tensor<T>

The input data to process.

Returns

Tensor<T>

The network's prediction.

Remarks

For Beginners: This is the main method you'll use to get results from your trained neural network. You provide some input data (like an image or text), and the network processes it through all its layers to produce an output (like a classification or prediction).

Restore(Tensor<T>)

Restores a video frame using the VRT model.

public Tensor<T> Restore(Tensor<T> input)

Parameters

input Tensor<T>

Input video frame(s) tensor [B, C, H, W] or [C, H, W].

Returns

Tensor<T>

Restored video frame tensor.

Remarks

For Beginners: This method enhances a video frame by: - Super-resolution: Making it higher resolution - Deblurring: Removing motion blur - Denoising: Removing visual noise

SerializeNetworkSpecificData(BinaryWriter)

Serializes network-specific data that is not covered by the general serialization process.

protected override void SerializeNetworkSpecificData(BinaryWriter writer)

Parameters

writer BinaryWriter

The BinaryWriter to write the data to.

Remarks

This method is called at the end of the general serialization process to allow derived classes to write any additional data specific to their implementation.

For Beginners: Think of this as packing a special compartment in your suitcase. While the main serialization method packs the common items (layers, parameters), this method allows each specific type of neural network to pack its own unique items that other networks might not have.

SuperResolve(Tensor<T>)

Performs video super-resolution.

public Tensor<T> SuperResolve(Tensor<T> lowResFrames)

Parameters

lowResFrames Tensor<T>

Low-resolution video frames.

Returns

Tensor<T>

High-resolution video frames.

Train(Tensor<T>, Tensor<T>)

Trains the neural network on a single input-output pair.

public override void Train(Tensor<T> input, Tensor<T> expectedOutput)

Parameters

input Tensor<T>

The input data.

expectedOutput Tensor<T>

The expected output for the given input.

Remarks

This method performs one training step on the neural network using the provided input and expected output. It updates the network's parameters to reduce the error between the network's prediction and the expected output.

For Beginners: This is how your neural network learns. You provide: - An input (what the network should process) - The expected output (what the correct answer should be)

The network then:

  1. Makes a prediction based on the input
  2. Compares its prediction to the expected output
  3. Calculates how wrong it was (the loss)
  4. Adjusts its internal values to do better next time

After training, you can get the loss value using the GetLastLoss() method to see how well the network is learning.

UpdateParameters(Vector<T>)

Updates the network's parameters with new values.

public override void UpdateParameters(Vector<T> parameters)

Parameters

parameters Vector<T>

The new parameter values to set.

Remarks

For Beginners: During training, a neural network's internal values (parameters) get adjusted to improve its performance. This method allows you to update all those values at once by providing a complete set of new parameters.

This is typically used by optimization algorithms that calculate better parameter values based on training data.

Edit this page