IC-FPS: Instance-Centroid Faster Point Sampling Module for 3D Point-base Object Detection

TL;DR

This paper introduces IC-FPS, a novel point sampling module that significantly enhances the efficiency and speed of 3D object detection models on large-scale point clouds, enabling real-time performance.

Contribution

The paper proposes IC-FPS, a new sampling module combining background filtering and centroid-based sampling, which replaces the computationally expensive FPS in point-based models.

Findings

Speeds up inference by 3.8 times on Waymo dataset

Enables real-time detection in large-scale point clouds

Improves baseline model performance significantly

Abstract

3D object detection is one of the most important tasks in autonomous driving and robotics. Our research focuses on tackling low efficiency issue of point-based methods on large-scale point clouds. Existing point-based methods adopt farthest point sampling (FPS) strategy for downsampling, which is computationally expensive in terms of inference time and memory consumption when the number of point cloud increases. In order to improve efficiency, we propose a novel Instance-Centroid Faster Point Sampling Module (IC-FPS) , which effectively replaces the first Set Abstraction (SA) layer that is extremely tedious. IC-FPS module is comprised of two methods, local feature diffusion based background point filter (LFDBF) and Centroid-Instance Sampling Strategy (CISS). LFDBF is constructed to exclude most invalid background points, while CISS substitutes FPS strategy by fast sampling centroids and instance points. IC-FPS module can be inserted to almost every point-based models. Extensive experiments on multiple public benchmarks have demonstrated the superiority of IC-FPS. On Waymo dataset, the proposed module significantly improves performance of baseline model and accelerates inference speed by 3.8 times. For the first time, real-time detection of point-based models in large-scale point cloud scenario is realized.