PointNetPlusPlus<T>
Models & Types · AiDotNet.PointCloud.Models
Implements the PointNet++ architecture for hierarchical point cloud processing.
Inheritance: NeuralNetworkBase<T> → PointNetPlusPlus<T>
Implements: IPointCloudClassification<T>, IPointCloudSegmentation<T>
For Beginners
PointNet++ extends PointNet by adding hierarchical feature learning at multiple scales.
How It Works
Key improvements over PointNet:
- Hierarchical structure: Processes point clouds at multiple resolutions
- Local context: Captures fine-grained local patterns
- Multi-scale grouping: Learns features at different scales simultaneously
- Better generalization: More robust to non-uniform point density
Architecture components:
- Set Abstraction Layers: Hierarchically group points and extract features
- Sampling: Select subset of points as centroids
- Grouping: Find neighboring points around each centroid
- PointNet layer: Extract features from each local region
- Feature Propagation Layers: Upsample features for segmentation tasks
- Interpolation: Propagate features from coarse to fine levels
- Skip connections: Combine with features from encoder
Why hierarchical learning matters:
- Different patterns exist at different scales (like edges vs. shapes in images)
- Local context provides detailed geometry information
- Global context provides overall shape understanding
- Combining both gives comprehensive understanding
Applications:
- Fine-grained classification
- Part segmentation (identifying specific parts of objects)
- Semantic segmentation (labeling each point)
- Better performance on complex, detailed shapes
Example use case - autonomous driving:
- Coarse level: Identify general object shapes (car, pedestrian)
- Medium level: Recognize object parts (wheels, windows)
- Fine level: Detect details (door handles, mirrors)
Reference: “PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space” by Qi et al., NeurIPS 2017
Example
// Create a PointNet++ model for hierarchical point cloud classification
var options = new AiDotNet.Models.Options.PointNetPlusPlusOptions
{
NumClasses = 40,
UseMultiScaleGrouping = true
};
var pointNetPP = new PointNetPlusPlus<float>(options);
Constructors
| Constructor | Summary |
|---|---|
PointNetPlusPlus() |
Initializes a new instance of the PointNetPlusPlus class with default options. |
PointNetPlusPlus(PointNetPlusPlusOptions options, ILossFunction<T> lossFunction, PointNetPlusPlusOptions modelOptions, IGradientBasedOptimizer<T, Tensor<T>, Tensor<T>> optimizer) |
Initializes a new instance of the PointNetPlusPlus class with configurable options. |
PointNetPlusPlus(int numClasses, int[] samplingRates, double[] searchRadii, int[][] mlpDimensions, ILossFunction<T> lossFunction) |
Initializes a new instance of the PointNetPlusPlus class. |
Properties
| Property | Summary |
|---|---|
bool SupportsTraining { get; } |
Methods
| Method | Summary |
|---|---|
ModelMetadata<T> GetModelMetadata() |
|
Tensor<T> ExtractPointFeatures(Tensor<T> pointCloud) |
|
Tensor<T> ForwardWithMemory(Tensor<T> input) |
|
Tensor<T> SegmentPointCloud(Tensor<T> pointCloud) |
|
Vector<T> ClassifyPointCloud(Tensor<T> pointCloud) |
|
Vector<T> ExtractGlobalFeatures(Tensor<T> pointCloud) |