# RoarNet: A Robust 3D Object Detection based on RegiOn Approximation Refinement

arXiv: https://arxiv.org/abs/1811.03818 · HTML: https://mlsanity.com/paper/1811.03818/

## Key facts

- Cited by 31 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 9 Nov 2018.

## Built on by (most cited first, 30 of 31)

- [TransFusion: Robust LiDAR-Camera Fusion for 3D Object Detection with Transformers](https://mlsanity.com/paper/2203.11496/) (2022)
- [3D Object Detection for Autonomous Driving: A Comprehensive Survey](https://mlsanity.com/paper/2206.09474/) (2022)
- [Multi-modal Sensor Fusion for Auto Driving Perception: A Survey](https://mlsanity.com/paper/2202.02703/) (2022)
- [Monocular 3D Object Detection: An Extrinsic Parameter Free Approach](https://mlsanity.com/paper/2106.15796/) (2021)
- [Multi-Modal 3D Object Detection in Autonomous Driving: a Survey](https://mlsanity.com/paper/2106.12735/) (2021)
- [Learning Monocular Depth in Dynamic Scenes via Instance-Aware Projection Consistency](https://mlsanity.com/paper/2102.02629/) (2021)
- [HRFuser: A Multi-resolution Sensor Fusion Architecture for 2D Object Detection](https://mlsanity.com/paper/2206.15157/) (2022)
- [Weakly Supervised Monocular 3D Object Detection using Multi-View Projection and Direction Consistency](https://mlsanity.com/paper/2303.08686/) (2023)
- [MonoATT: Online Monocular 3D Object Detection with Adaptive Token Transformer](https://mlsanity.com/paper/2303.13018/) (2023)
- [MultiCorrupt: A Multi-Modal Robustness Dataset and Benchmark of LiDAR-Camera Fusion for 3D Object Detection](https://mlsanity.com/paper/2402.11677/) (2024)
- [Adversarial Attacks on Camera-LiDAR Models for 3D Car Detection](https://mlsanity.com/paper/2103.09448/) (2021)
- [Towards Universal Physical Attacks On Cascaded Camera-Lidar 3D Object Detection Models](https://mlsanity.com/paper/2101.10747/) (2021)
- [Transformers for Multi-Object Tracking on Point Clouds](https://mlsanity.com/paper/2205.15730/) (2022)
- [3D Dual-Fusion: Dual-Domain Dual-Query Camera-LiDAR Fusion for 3D Object Detection](https://mlsanity.com/paper/2211.13529/) (2022)
- [MoGDE: Boosting Mobile Monocular 3D Object Detection with Ground Depth Estimation](https://mlsanity.com/paper/2303.13561/) (2023)
- [Robust 3D Object Detection in Cold Weather Conditions](https://mlsanity.com/paper/2205.11925/) (2022)
- [SST-Calib: Simultaneous Spatial-Temporal Parameter Calibration between LIDAR and Camera](https://mlsanity.com/paper/2207.03704/) (2022)
- [A Survey of Multi-sensor Fusion Perception for Embodied AI: Background, Methods, Challenges and Prospects](https://mlsanity.com/paper/2506.19769/) (2025)
- [Survey and Systematization of 3D Object Detection Models and Methods](https://mlsanity.com/paper/2201.09354/) (2022)
- [Center Feature Fusion: Selective Multi-Sensor Fusion of Center-based Objects](https://mlsanity.com/paper/2209.12880/) (2022)
- [Anyview: Generalizable Indoor 3D Object Detection with Variable Frames](https://mlsanity.com/paper/2310.05346/) (2023)
- [Integrating Multi-Modal Sensors: A Review of Fusion Techniques for Intelligent Vehicles](https://mlsanity.com/paper/2506.21885/) (2025)
- [Object Detection in 3D Point Clouds via Local Correlation-Aware Point Embedding](https://mlsanity.com/paper/2301.04613/) (2023)
- [Revisiting Cross-Domain Problem for LiDAR-based 3D Object Detection](https://mlsanity.com/paper/2408.12708/) (2024)
- [PV-SSD: A Multi-Modal Point Cloud Feature Fusion Method for Projection Features and Variable Receptive Field Voxel Features](https://mlsanity.com/paper/2308.06791/) (2023)
- [End-to-End 3D Object Detection using LiDAR Point Cloud](https://mlsanity.com/paper/2312.15377/) (2023)
- [3D-FFS: Faster 3D object detection with Focused Frustum Search in sensor fusion based networks](https://mlsanity.com/paper/2103.08294/) (2021)
- [GOOD: General Optimization-based Fusion for 3D Object Detection via LiDAR-Camera Object Candidates](https://mlsanity.com/paper/2303.09800/) (2023)
- [MonoLite3D: Lightweight 3D Object Properties Estimation](https://mlsanity.com/paper/2503.02201/) (2025)
- [FrustumFusionNets: A Three-Dimensional Object Detection Network Based on Tractor Road Scene](https://mlsanity.com/paper/2503.13951/) (2025)

## Abstract (arXiv)

We present RoarNet, a new approach for 3D object detection from a 2D image and 3D Lidar point clouds. Based on two-stage object detection framework with PointNet as our backbone network, we suggest several novel ideas to improve 3D object detection performance. The first part of our method, RoarNet_2D, estimates the 3D poses of objects from a monocular image, which approximates where to examine further, and derives multiple candidates that are geometrically feasible. This step significantly narrows down feasible 3D regions, which otherwise requires demanding processing of 3D point clouds in a huge search space. Then the second part, RoarNet_3D, takes the candidate regions and conducts in-depth inferences to conclude final poses in a recursive manner. Inspired by PointNet, RoarNet_3D processes 3D point clouds directly without any loss of data, leading to precise detection. We evaluate our method in KITTI, a 3D object detection benchmark. Our result shows that RoarNet has superior performance to state-of-the-art methods that are publicly available. Remarkably, RoarNet also outperforms state-of-the-art methods even in settings where Lidar and camera are not time synchronized, which is practically important for actual driving environments. RoarNet is implemented in Tensorflow and publicly available with pre-trained models.