FuStaOptions

Options & Configuration · AiDotNet.Video.Options

Configuration options for the FuSta (Full-frame Stabilization) video stabilization model.

Inheritance: ModelOptions → FuStaOptions

For Beginners

FuSta options configure the fusion-based video stabilization model.

How It Works

References:

  • Paper: “FuSta: Hybrid Approach for Full-frame Video Stabilization” (Liu et al., 2021)

FuSta combines optical flow-based warping with outpainting to achieve full-frame stabilization without cropping, using a two-stage pipeline: motion compensation + content completion.

Constructors

Constructor Summary
FuStaOptions() Initializes a new instance with default values.
FuStaOptions(FuStaOptions 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 NumFeatures { get; set; } Number of base feature channels in the stabilization network.
int NumHeads { get; set; } Number of attention heads for the content completion transformer.
int NumLevels { get; set; } Number of encoder-decoder levels in the outpainting branch.
int NumResBlocks { get; set; } Number of residual blocks in each encoder-decoder level.
string ModelPath { get; set; } Path to the ONNX model file for inference mode.