FlowLensOptions
Options & Configuration · AiDotNet.Video.Options
Configuration options for the FlowLens video inpainting model.
Inheritance: ModelOptions → FlowLensOptions
For Beginners
FlowLens options configure the flow-guided video inpainting model.
How It Works
References:
- Paper: “FlowLens: Seeing Beyond the FoV via Optical Flow Completion” (Xu et al., ECCV 2022)
FlowLens completes optical flow in masked regions first, then uses the completed flow for high-quality temporal propagation followed by a refinement network, decoupling motion estimation from pixel synthesis.
Constructors
| Constructor | Summary |
|---|---|
FlowLensOptions() |
Initializes a new instance with default values. |
FlowLensOptions(FlowLensOptions 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. |
int NumFlowIters { get; set; } |
Number of flow completion iterations for refining estimated flow in masked regions. |
int NumLevels { get; set; } |
Number of encoder-decoder levels in the refinement network. |
int NumResBlocks { get; set; } |
Number of residual blocks in the refinement branch. |
string ModelPath { get; set; } |
Path to the ONNX model file for inference mode. |