FastDVDNet<T>

Models & Types · AiDotNet.Video.Denoising

FastDVDNet: Towards Real-Time Deep Video Denoising Without Flow Estimation.

Inheritance: NeuralNetworkBase<T> → VideoNeuralNetworkBase<T> → VideoDenoisingBase<T> → FastDVDNet<T>

For Beginners

FastDVDNet removes noise from video while preserving details and maintaining temporal consistency across frames. Unlike image denoisers, it uses multiple frames to reduce noise more effectively.

Key advantages:

  • Real-time video denoising
  • No optical flow computation needed
  • Handles various noise levels
  • Preserves temporal consistency

Example usage:

How It Works

Technical Details:

  • Two-stage denoising pipeline
  • Stage 1: Denoise groups of 3 frames
  • Stage 2: Fuse stage 1 outputs temporally
  • Noise map as additional input for noise-level adaptation

Reference: “FastDVDnet: Towards Real-Time Deep Video Denoising Without Flow Estimation” https://arxiv.org/abs/1907.01361

Constructors

Constructor Summary
FastDVDNet() Initializes a new instance with default architecture settings.
FastDVDNet(NeuralNetworkArchitecture<T> architecture, FastDVDNetOptions options, IGradientBasedOptimizer<T, Tensor<T>, Tensor<T>> optimizer, ILossFunction<T> lossFunction)
FastDVDNet(NeuralNetworkArchitecture<T> architecture, string onnxModelPath, FastDVDNetOptions options)

Properties

Property Summary
bool SupportsTraining { get; }

Methods

Method Summary
List<Tensor<T>> Denoise(List<Tensor<T>> frames, double noiseLevel) Denoises a sequence of video frames.
ModelMetadata<T> GetModelMetadata()
Tensor<T> AddGaussianNoise(Tensor<T> frame, double sigma) Adds synthetic noise to frames for testing.
Tensor<T> Denoise(Tensor<T> noisyFrames)
Tensor<T> DenoiseFrame(List<Tensor<T>> neighborFrames, double noiseLevel) Denoises a single frame using neighboring frames.
double EstimateNoiseLevel(Tensor<T> frame) Estimates the noise level in a frame.