CVMay 23, 2023

Hierarchical Adaptive Voxel-guided Sampling for Real-time Applications in Large-scale Point Clouds

arXiv:2305.14306v1Has Code
Originality Highly original
AI Analysis

This addresses the bottleneck in real-time processing of scene-level point clouds for tasks like detection and segmentation, offering a significant efficiency improvement with minimal integration effort.

The paper tackles the inefficiency of point sampling in large-scale point clouds by proposing a hierarchical adaptive voxel-guided sampler that achieves competitive performance with farthest point sampling while being over 100 times faster, enabling real-time applications.

While point-based neural architectures have demonstrated their efficacy, the time-consuming sampler currently prevents them from performing real-time reasoning on scene-level point clouds. Existing methods attempt to overcome this issue by using random sampling strategy instead of the commonly-adopted farthest point sampling~(FPS), but at the expense of lower performance. So the effectiveness/efficiency trade-off remains under-explored. In this paper, we reveal the key to high-quality sampling is ensuring an even spacing between points in the subset, which can be naturally obtained through a grid. Based on this insight, we propose a hierarchical adaptive voxel-guided point sampler with linear complexity and high parallelization for real-time applications. Extensive experiments on large-scale point cloud detection and segmentation tasks demonstrate that our method achieves competitive performance with the most powerful FPS, at an amazing speed that is more than 100 times faster. This breakthrough in efficiency addresses the bottleneck of the sampling step when handling scene-level point clouds. Furthermore, our sampler can be easily integrated into existing models and achieves a 20$\sim$80\% reduction in runtime with minimal effort. The code will be available at https://github.com/OuyangJunyuan/pointcloud-3d-detector-tensorrt

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes