Table of Contents

Class DepthAnythingV2<T>

Namespace
AiDotNet.Video.Depth
Assembly
AiDotNet.dll

Depth Anything V2 for monocular depth estimation.

public class DepthAnythingV2<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 (e.g., float, double).

Inheritance
DepthAnythingV2<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

For Beginners: Depth Anything V2 is a state-of-the-art model for estimating depth maps from single images (monocular depth estimation). Given an RGB image, it predicts the relative distance of each pixel from the camera. This is useful for: - 3D scene understanding - Augmented reality applications - Autonomous driving - Video editing and VFX - Object detection and segmentation

Unlike stereo depth estimation which requires two cameras, Depth Anything works with a single image by learning depth cues from large-scale training data.

Technical Details: - Vision Transformer (ViT) based encoder with DINOv2 initialization - Efficient multi-scale decoder for dense prediction - Scale-invariant depth loss for robust training - Supports various backbone sizes (Small, Base, Large)

Reference: Yang et al., "Depth Anything V2" 2024.

Constructors

DepthAnythingV2(NeuralNetworkArchitecture<T>, IGradientBasedOptimizer<T, Tensor<T>, Tensor<T>>?, ILossFunction<T>?, ModelSize)

Initializes a new instance of the DepthAnythingV2 class in native (trainable) mode.

public DepthAnythingV2(NeuralNetworkArchitecture<T> architecture, IGradientBasedOptimizer<T, Tensor<T>, Tensor<T>>? optimizer = null, ILossFunction<T>? lossFunction = null, DepthAnythingV2<T>.ModelSize modelSize = ModelSize.Base)

Parameters

architecture NeuralNetworkArchitecture<T>

The neural network architecture configuration.

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

Optional optimizer for training.

lossFunction ILossFunction<T>

Optional loss function (default: ScaleInvariantDepthLoss).

modelSize DepthAnythingV2<T>.ModelSize

The model size variant.

Remarks

For Beginners: This constructor creates a trainable Depth Anything V2 model. Use this when you want to train or fine-tune the model on your own depth data.

DepthAnythingV2(NeuralNetworkArchitecture<T>, string, ModelSize)

Initializes a new instance of the DepthAnythingV2 class in ONNX (inference-only) mode.

public DepthAnythingV2(NeuralNetworkArchitecture<T> architecture, string onnxModelPath, DepthAnythingV2<T>.ModelSize modelSize = ModelSize.Base)

Parameters

architecture NeuralNetworkArchitecture<T>

The neural network architecture configuration.

onnxModelPath string

Path to the ONNX model file.

modelSize DepthAnythingV2<T>.ModelSize

The model size variant for configuration.

Remarks

For Beginners: This constructor loads a pre-trained Depth Anything V2 model from ONNX format. Use this for fast inference when you don't need to train the model.

Properties

SupportsTraining

Gets whether training is supported.

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.

Dispose(bool)

Disposes of managed resources, including the ONNX inference session.

protected override void Dispose(bool disposing)

Parameters

disposing bool

True if disposing, false if finalizing.

EstimateDepth(Tensor<T>)

Estimates depth from an RGB image.

public Tensor<T> EstimateDepth(Tensor<T> image)

Parameters

image Tensor<T>

Input image tensor [C, H, W] or [B, C, H, W].

Returns

Tensor<T>

Depth map tensor [H, W] or [B, 1, H, W] with relative depth values.

EstimateVideoDepth(List<Tensor<T>>)

Estimates depth for a sequence of video frames.

public List<Tensor<T>> EstimateVideoDepth(List<Tensor<T>> frames)

Parameters

frames List<Tensor<T>>

List of video frames.

Returns

List<Tensor<T>>

List of depth maps for each frame.

GetDepthAtPoint(Tensor<T>, int, int)

Gets the relative depth value at a specific point.

public double GetDepthAtPoint(Tensor<T> depthMap, int x, int y)

Parameters

depthMap Tensor<T>

The depth map tensor.

x int

X coordinate.

y int

Y coordinate.

Returns

double

Relative depth value at the specified point.

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