PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation
2025/8/26小于 1 分钟
What is the idea?
The point cloud has no order like image, so use multi-layer perceptron (MLP) to map the cloud to a fixed-size feature vector.
The point cloud has no order like image, so use multi-layer perceptron (MLP) to map the cloud to a fixed-size feature vector.