# Fast Point R-CNN

arXiv: https://arxiv.org/abs/1908.02990 · HTML: https://mlsanity.com/paper/1908.02990/

## Key facts

- Cited by 119 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 8 Aug 2019.

## Built on by (most cited first, 30 of 119)

- [BEVFusion: Multi-Task Multi-Sensor Fusion with Unified Bird's-Eye View Representation](https://mlsanity.com/paper/2205.13542/) (2022)
- [PV-RCNN++: Point-Voxel Feature Set Abstraction With Local Vector Representation for 3D Object Detection](https://mlsanity.com/paper/2102.00463/) (2021)
- [Self-Supervised Pretraining of 3D Features on any Point-Cloud](https://mlsanity.com/paper/2101.02691/) (2021)
- [Embracing Single Stride 3D Object Detector with Sparse Transformer](https://mlsanity.com/paper/2112.06375/) (2021)
- [PandaSet: Advanced Sensor Suite Dataset for Autonomous Driving](https://mlsanity.com/paper/2112.12610/) (2021)
- [Multimodal Virtual Point 3D Detection](https://mlsanity.com/paper/2111.06881/) (2021)
- [Offboard 3D Object Detection from Point Cloud Sequences](https://mlsanity.com/paper/2103.05073/) (2021)
- [3D Object Detection for Autonomous Driving: A Comprehensive Survey](https://mlsanity.com/paper/2206.09474/) (2022)
- [Not All Points Are Equal: Learning Highly Efficient Point-based Detectors for 3D LiDAR Point Clouds](https://mlsanity.com/paper/2203.11139/) (2022)
- [LiDAR R-CNN: An Efficient and Universal 3D Object Detector](https://mlsanity.com/paper/2103.15297/) (2021)
- [SE-SSD: Self-Ensembling Single-Stage Object Detector From Point Cloud](https://mlsanity.com/paper/2104.09804/) (2021)
- [3D Object Detection for Autonomous Driving: A Survey](https://mlsanity.com/paper/2106.10823/) (2021)
- [Voxel Set Transformer: A Set-to-Set Approach to 3D Object Detection from Point Clouds](https://mlsanity.com/paper/2203.10314/) (2022)
- [SPG: Unsupervised Domain Adaptation for 3D Object Detection via Semantic Point Generation](https://mlsanity.com/paper/2108.06709/) (2021)
- [Sparse Fuse Dense: Towards High Quality 3D Detection with Depth Completion](https://mlsanity.com/paper/2203.09780/) (2022)
- [M3DeTR: Multi-representation, Multi-scale, Mutual-relation 3D Object Detection with Transformers](https://mlsanity.com/paper/2104.11896/) (2021)
- [FlatFormer: Flattened Window Attention for Efficient Point Cloud Transformer](https://mlsanity.com/paper/2301.08739/) (2023)
- [PointCutMix: Regularization Strategy for Point Cloud Classification](https://mlsanity.com/paper/2101.01461/) (2021)
- [Motion Inspired Unsupervised Perception and Prediction in Autonomous Driving](https://mlsanity.com/paper/2210.08061/) (2022)
- [Behind the Curtain: Learning Occluded Shapes for 3D Object Detection](https://mlsanity.com/paper/2112.02205/) (2021)
- [Occupancy-MAE: Self-supervised Pre-training Large-scale LiDAR Point Clouds with Masked Occupancy Autoencoders](https://mlsanity.com/paper/2206.09900/) (2022)
- [FocalFormer3D : Focusing on Hard Instance for 3D Object Detection](https://mlsanity.com/paper/2308.04556/) (2023)
- [IS-Fusion: Instance-Scene Collaborative Fusion for Multimodal 3D Object Detection](https://mlsanity.com/paper/2403.15241/) (2024)
- [Polar Parametrization for Vision-based Surround-View 3D Detection](https://mlsanity.com/paper/2206.10965/) (2022)
- [SASA: Semantics-Augmented Set Abstraction for Point-based 3D Object Detection](https://mlsanity.com/paper/2201.01976/) (2022)
- [SAFDNet: A Simple and Effective Network for Fully Sparse 3D Object Detection](https://mlsanity.com/paper/2403.05817/) (2024)
- [Learning Semantic Segmentation of Large-Scale Point Clouds with Random Sampling](https://mlsanity.com/paper/2107.02389/) (2021)
- [3D Object Tracking with Transformer](https://mlsanity.com/paper/2110.14921/) (2021)
- [EPNet++: Cascade Bi-directional Fusion for Multi-Modal 3D Object Detection](https://mlsanity.com/paper/2112.11088/) (2021)
- [VPFNet: Improving 3D Object Detection with Virtual Point based LiDAR and Stereo Data Fusion](https://mlsanity.com/paper/2111.14382/) (2021)

## Abstract (arXiv)

We present a unified, efficient and effective framework for point-cloud based 3D object detection. Our two-stage approach utilizes both voxel representation and raw point cloud data to exploit respective advantages. The first stage network, with voxel representation as input, only consists of light convolutional operations, producing a small number of high-quality initial predictions. Coordinate and indexed convolutional feature of each point in initial prediction are effectively fused with the attention mechanism, preserving both accurate localization and context information. The second stage works on interior points with their fused feature for further refining the prediction. Our method is evaluated on KITTI dataset, in terms of both 3D and Bird's Eye View (BEV) detection, and achieves state-of-the-arts with a 15FPS detection rate.