ThreeDVLMOptions
Options & Configuration · AiDotNet.VisionLanguage.ThreeD
Base configuration options for 3D vision-language models.
Inheritance: ModelOptions → GenerativeVLMOptions → ThreeDVLMOptions
Known derived types: GPT4PointOptions, LEOVLOptions, PointLLMOptions, SceneLLMOptions, ThreeDGraphLLMOptions, ThreeDLLMOptions
For Beginners
These options configure the ThreeD model. Default values follow the original paper settings.
Constructors
| Constructor | Summary |
|---|---|
ThreeDVLMOptions() |
Initializes a new instance with default values. |
ThreeDVLMOptions(ThreeDVLMOptions other) |
Initializes a new instance by copying from another instance. |
Properties
| Property | Summary |
|---|---|
int MaxPoints { get; set; } |
Gets or sets the maximum number of 3D points the model can process. |
int PointChannels { get; set; } |
Gets or sets the number of channels per point (3=XYZ, 6=XYZ+RGB, 9=XYZ+RGB+normals). |
int PointEncoderDim { get; set; } |
Gets or sets the point cloud encoder hidden dimension. |
string LanguageModelName { get; set; } |
Gets or sets the language model backbone name. |