FastPoint: Accelerating 3D Point Cloud Model Inference via Sample Point Distance Prediction
This work addresses computational bottlenecks in 3D point cloud processing for applications like autonomous driving and robotics, representing a strong incremental improvement to existing methods.
The paper tackles the challenge of efficiently processing large and irregular 3D point clouds by introducing FastPoint, a software-based acceleration technique that predicts distance trends during farthest point sampling to avoid exhaustive distance computations. This approach achieves a 2.55x end-to-end speedup on NVIDIA RTX 3090 GPU while maintaining accuracy.
Deep neural networks have revolutionized 3D point cloud processing, yet efficiently handling large and irregular point clouds remains challenging. To tackle this problem, we introduce FastPoint, a novel software-based acceleration technique that leverages the predictable distance trend between sampled points during farthest point sampling. By predicting the distance curve, we can efficiently identify subsequent sample points without exhaustively computing all pairwise distances. Our proposal substantially accelerates farthest point sampling and neighbor search operations while preserving sampling quality and model performance. By integrating FastPoint into state-of-the-art 3D point cloud models, we achieve 2.55x end-to-end speedup on NVIDIA RTX 3090 GPU without sacrificing accuracy.