PWStableNetOptions
Options & Configuration · AiDotNet.Video.Options
Configuration options for the PWStableNet (Pixel-Wise Stable Net) video stabilization model.
Inheritance: ModelOptions → PWStableNetOptions
For Beginners
PWStableNet options configure the pixel-wise video stabilization model.
How It Works
References:
- Paper: “PWStableNet: Learning Pixel-Wise Warping Maps for Video Stabilization” (Zhao et al., IEEE TIP 2020)
PWStableNet predicts per-pixel warping maps (not global homographies) for more flexible stabilization that handles parallax and rolling shutter distortion.
Constructors
| Constructor | Summary |
|---|---|
PWStableNetOptions() |
Initializes a new instance with default values. |
PWStableNetOptions(PWStableNetOptions 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 GridSize { get; set; } |
Grid size for the spatial transformer network that produces warp fields. |
int NumFeatures { get; set; } |
Number of base feature channels. |
int NumRefinementIters { get; set; } |
Number of coarse-to-fine refinement iterations for the warp field. |
int NumResBlocks { get; set; } |
Number of residual blocks in the feature extraction backbone. |
string ModelPath { get; set; } |
Path to the ONNX model file for inference mode. |