GaVSOptions
Options & Configuration · AiDotNet.Video.Options
Configuration options for the GaVS (Gaze-aware Video Stabilization) model.
Inheritance: ModelOptions → GaVSOptions
For Beginners
GaVS options configure the adversarial video stabilization model.
How It Works
References:
- Paper: “Gaze-aware Video Stabilization” (2023)
GaVS incorporates gaze prediction to stabilize video while preserving the viewer’s region of interest, weighting stabilization strength based on visual saliency.
Constructors
| Constructor | Summary |
|---|---|
GaVSOptions() |
Initializes a new instance with default values. |
GaVSOptions(GaVSOptions other) |
Initializes a new instance by copying from another instance. |
Properties
| Property | Summary |
|---|---|
OnnxModelOptions OnnxOptions { get; set; } |
ONNX runtime options for inference mode. |
VideoModelVariant Variant { get; set; } |
Model variant controlling capacity and speed trade-off. |
double DropoutRate { get; set; } |
Dropout rate for regularization. |
double LearningRate { get; set; } |
Learning rate for training. |
int GazeHiddenDim { get; set; } |
Hidden dimension for the gaze prediction branch. |
int NumFeatures { get; set; } |
Number of base feature channels. |
int NumGazeHeads { get; set; } |
Number of gaze prediction heads for multi-scale saliency estimation. |
int SmoothingWindow { get; set; } |
Smoothing window size for trajectory filtering. |
string ModelPath { get; set; } |
Path to the ONNX model file for inference mode. |