ThreeDMFOptions
Options & Configuration · AiDotNet.Video.Options
Configuration options for the 3DMF (3D Motion Field) video stabilization model.
Inheritance: ModelOptions → ThreeDMFOptions
For Beginners
3DMF options configure the 3D motion field video stabilizer.
How It Works
References:
- Paper: “3D Video Stabilization with Depth Estimation by CNN-based Optimization” (Lee & Lee, CVPR 2021)
3DMF estimates depth and 3D camera motion to perform stabilization in 3D space, better handling parallax and depth-dependent motion than 2D methods.
Constructors
| Constructor | Summary |
|---|---|
ThreeDMFOptions() |
Initializes a new instance with default values. |
ThreeDMFOptions(ThreeDMFOptions 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 NumDepthLayers { get; set; } |
Number of depth estimation layers in the depth prediction branch. |
int NumFeatures { get; set; } |
Number of base feature channels. |
int NumMotionIters { get; set; } |
Number of 3D motion estimation refinement iterations. |
int NumResBlocks { get; set; } |
Number of residual blocks in the feature backbone. |
string ModelPath { get; set; } |
Path to the ONNX model file for inference mode. |