PG-RCNN: Semantic Surface Point Generation for 3D Object Detection

TL;DR

PG-RCNN introduces an end-to-end 3D object detection method that generates semantic surface points for foreground objects, improving detection accuracy with fewer parameters by leveraging shape and semantic information.

Contribution

It proposes a novel RoI point generation module that estimates complete object shapes and semantic features, enhancing 3D detection performance over existing methods.

Findings

Improves detection accuracy on KITTI benchmark.

Generates geometrically and semantically rich point clouds.

Uses fewer parameters than state-of-the-art models.

Abstract

One of the main challenges in LiDAR-based 3D object detection is that the sensors often fail to capture the complete spatial information about the objects due to long distance and occlusion. Two-stage detectors with point cloud completion approaches tackle this problem by adding more points to the regions of interest (RoIs) with a pre-trained network. However, these methods generate dense point clouds of objects for all region proposals, assuming that objects always exist in the RoIs. This leads to the indiscriminate point generation for incorrect proposals as well. Motivated by this, we propose Point Generation R-CNN (PG-RCNN), a novel end-to-end detector that generates semantic surface points of foreground objects for accurate detection. Our method uses a jointly trained RoI point generation module to process the contextual information of RoIs and estimate the complete shape and displacement of foreground objects. For every generated point, PG-RCNN assigns a semantic feature that indicates the estimated foreground probability. Extensive experiments show that the point clouds generated by our method provide geometrically and semantically rich information for refining false positive and misaligned proposals. PG-RCNN achieves competitive performance on the KITTI benchmark, with significantly fewer parameters than state-of-the-art models. The code is available at https://github.com/quotation2520/PG-RCNN.