# PointRGCN: Graph Convolution Networks for 3D Vehicles Detection Refinement

Source: [PointRGCN: Graph Convolution Networks for 3D Vehicles Detection Refinement](<https://www.sota2.com/research/paper/68fa66b11e209131cea11d43>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-01-04T03:14:09.916Z

Authors: Jesus Zarzar, Silvio Giancola, Bernard Ghanem

Published: 2019-11-27T15:51:49.000Z

## Abstract

In autonomous driving pipelines, perception modules provide a visual understanding of the surrounding road scene. Among the perception tasks, vehicle detection is of paramount importance for a safe driving as it identifies the position of other agents sharing the road. In our work, we propose PointRGCN: a graph-based 3D object detection pipeline based on graph convolutional networks (GCNs) which operates exclusively on 3D LiDAR point clouds. To perform more accurate 3D object detection, we leverage a graph representation that performs proposal feature and context aggregation. We integrate residual GCNs in a two-stage 3D object detection pipeline, where 3D object proposals are refined using a novel graph representation. In particular, R-GCN is a residual GCN that classifies and regresses 3D proposals, and C-GCN is a contextual GCN that further refines proposals by sharing contextual information between multiple proposals. We integrate our refinement modules into a novel 3D detection pipeline, PointRGCN, and achieve state-of-the-art performance on the easy difficulty for the bird eye view detection task.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [3D Object Detection on KITTI (test)](<https://www.sota2.com/research/sota/3d-object-detection-on-kitti-test.md>): 3D Object Detection; KITTI (test); AP\_3D (Easy): 85.97.

- [BEV Object Detection on KITTI (test)](<https://www.sota2.com/research/sota/bev-object-detection-on-kitti-test.md>): BEV Object Detection; KITTI (test); AP (Easy): 91.91.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/1911.12236>)

[PDF](<https://arxiv.org/pdf/1911.12236.pdf>)
