Table of Contents

Class BasicVSRPlusPlus<T>

Namespace
AiDotNet.Video.Enhancement
Assembly
AiDotNet.dll

BasicVSR++ (Basic Video Super-Resolution++) for temporal video super-resolution.

public class BasicVSRPlusPlus<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
BasicVSRPlusPlus<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

BasicVSR++ improves upon BasicVSR with: - Second-order grid propagation for better temporal modeling - Flow-guided deformable alignment for accurate feature alignment - Bidirectional propagation for utilizing both past and future frames

For Beginners: BasicVSR++ is a video super-resolution model that upscales low-resolution videos to higher resolution while maintaining temporal consistency. Unlike single-image methods (like RealESRGAN), it uses information from multiple frames to produce sharper and more consistent results.

Key concepts:

  1. Bidirectional Propagation: Uses both past and future frames to enhance the current frame, ensuring temporal coherence.
  2. Optical Flow: Estimates how pixels move between frames to align features.
  3. Deformable Alignment: Uses learned offsets to precisely align features even with complex motions.

Example usage:

// Create architecture for video input
var arch = new NeuralNetworkArchitecture<double>(
    inputType: InputType.ThreeDimensional,
    inputHeight: 64, inputWidth: 64, inputDepth: 3);

// Create model with 4x upscaling
var model = new BasicVSRPlusPlus<double>(arch, scaleFactor: 4);

// Super-resolve video frames (shape: [numFrames, 3, H, W])
var highResFrames = model.EnhanceVideo(lowResFrames);

Reference: Chan et al., "BasicVSR++: Improving Video Super-Resolution with Enhanced Propagation and Alignment", CVPR 2022. https://arxiv.org/abs/2104.13371

Constructors

BasicVSRPlusPlus(NeuralNetworkArchitecture<T>, int, int, int, int, double)

Creates a BasicVSR++ model for native training and inference.

public BasicVSRPlusPlus(NeuralNetworkArchitecture<T> architecture, int scaleFactor = 4, int numFeatures = 64, int numResidualBlocks = 15, int numPropagations = 2, double learningRate = 0.0001)

Parameters

architecture NeuralNetworkArchitecture<T>

The neural network architecture configuration.

scaleFactor int

Upscaling factor (2 or 4). Default: 4.

numFeatures int

Number of feature channels. Default: 64.

numResidualBlocks int

Number of residual blocks. Default: 15.

numPropagations int

Number of propagation iterations. Default: 2.

learningRate double

Learning rate for training. Default: 0.0001.

Remarks

For Beginners: Create a BasicVSR++ model with sensible defaults: 

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

For faster training (lower quality):

var model = new BasicVSRPlusPlus<double>(arch,
    scaleFactor: 2,
    numFeatures: 32,
    numResidualBlocks: 8);

BasicVSRPlusPlus(NeuralNetworkArchitecture<T>, string, int, int, int, int)

Creates a BasicVSR++ model using a pretrained ONNX model for inference.

public BasicVSRPlusPlus(NeuralNetworkArchitecture<T> architecture, string onnxModelPath, int scaleFactor = 4, int numFeatures = 64, int numResidualBlocks = 15, int numPropagations = 2)

Parameters

architecture NeuralNetworkArchitecture<T>

The neural network architecture configuration.

onnxModelPath string

Path to the pretrained ONNX model.

scaleFactor int

Upscaling factor of the pretrained model. Default: 4.

numFeatures int

Number of feature channels in the model. Default: 64 (standard BasicVSR++ architecture).

numResidualBlocks int

Number of residual blocks. Default: 15 (standard BasicVSR++ architecture).

numPropagations int

Number of propagation iterations. Default: 2 (standard BasicVSR++ architecture).

Remarks

For Beginners: Use this when you have a pretrained BasicVSR++ model: 

var arch = new NeuralNetworkArchitecture<double>(
    inputType: InputType.ThreeDimensional,
    inputHeight: 64, inputWidth: 64, inputDepth: 3);
var model = new BasicVSRPlusPlus<double>(arch, "basicvsrpp_x4.onnx");
var hrFrames = model.EnhanceVideo(lrFrames);

Note: The architecture parameters (numFeatures, numResidualBlocks, numPropagations) default to the standard BasicVSR++ values. If your ONNX model uses a different architecture, provide the correct values to ensure accurate metadata reporting.

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.

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.

EnhanceVideo(Tensor<T>)

Enhances a sequence of video frames using temporal super-resolution.

public Tensor<T> EnhanceVideo(Tensor<T> frames)

Parameters

frames Tensor<T>

Input frames tensor with shape [numFrames, channels, height, width].

Returns

Tensor<T>

Enhanced frames tensor with shape [numFrames, channels, heightscale, widthscale].

Remarks

For Beginners: Pass your low-resolution video frames as a 4D tensor: 

// Load video frames into tensor [numFrames, 3, H, W]
var lrFrames = LoadVideoFrames("input.mp4");
var hrFrames = model.EnhanceVideo(lrFrames);
SaveVideoFrames(hrFrames, "output_4x.mp4");

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).

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.

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