# Object-Centric Stereo Matching for 3D Object Detection

arXiv: https://arxiv.org/abs/1909.07566 · HTML: https://mlsanity.com/paper/1909.07566/

## Key facts

- Cited by 29 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 17 Sep 2019.

## Built on by (most cited first, 29 of 29)

- [Categorical Depth Distribution Network for Monocular 3D Object Detection](https://mlsanity.com/paper/2103.01100/) (2021)
- [3D Object Detection for Autonomous Driving: A Comprehensive Survey](https://mlsanity.com/paper/2206.09474/) (2022)
- [SPG: Unsupervised Domain Adaptation for 3D Object Detection via Semantic Point Generation](https://mlsanity.com/paper/2108.06709/) (2021)
- [LIGA-Stereo: Learning LiDAR Geometry Aware Representations for Stereo-based 3D Detector](https://mlsanity.com/paper/2108.08258/) (2021)
- [3D Object Detection from Images for Autonomous Driving: A Survey](https://mlsanity.com/paper/2202.02980/) (2022)
- [Multi-Modal 3D Object Detection in Autonomous Driving: a Survey](https://mlsanity.com/paper/2106.12735/) (2021)
- [YOLOStereo3D: A Step Back to 2D for Efficient Stereo 3D Detection](https://mlsanity.com/paper/2103.09422/) (2021)
- [FGR: Frustum-Aware Geometric Reasoning for Weakly Supervised 3D Vehicle Detection](https://mlsanity.com/paper/2105.07647/) (2021)
- [Robustness of Object Detectors in Degrading Weather Conditions](https://mlsanity.com/paper/2106.08795/) (2021)
- [Homogeneous Multi-modal Feature Fusion and Interaction for 3D Object Detection](https://mlsanity.com/paper/2210.09615/) (2022)
- [Forging Vision Foundation Models for Autonomous Driving: Challenges, Methodologies, and Opportunities](https://mlsanity.com/paper/2401.08045/) (2024)
- [PLUMENet: Efficient 3D Object Detection from Stereo Images](https://mlsanity.com/paper/2101.06594/) (2021)
- [Stereo CenterNet based 3D Object Detection for Autonomous Driving](https://mlsanity.com/paper/2103.11071/) (2021)
- [DSGN++: Exploiting Visual-Spatial Relation for Stereo-based 3D Detectors](https://mlsanity.com/paper/2204.03039/) (2022)
- [Milestones in Autonomous Driving and Intelligent Vehicles Part II: Perception and Planning](https://mlsanity.com/paper/2306.01980/) (2023)
- [Know Your Surroundings: Panoramic Multi-Object Tracking by Multimodality Collaboration](https://mlsanity.com/paper/2105.14683/) (2021)
- [ESGN: Efficient Stereo Geometry Network for Fast 3D Object Detection](https://mlsanity.com/paper/2111.14055/) (2021)
- [StereoDistill: Pick the Cream from LiDAR for Distilling Stereo-based 3D Object Detection](https://mlsanity.com/paper/2301.01615/) (2023)
- [UrbanNet: Leveraging Urban Maps for Long Range 3D Object Detection](https://mlsanity.com/paper/2110.05561/) (2021)
- [Sparse LiDAR and Stereo Fusion (SLS-Fusion) for Depth Estimationand 3D Object Detection](https://mlsanity.com/paper/2103.03977/) (2021)
- [Transformer-based stereo-aware 3D object detection from binocular images](https://mlsanity.com/paper/2304.11906/) (2023)
- [Multistream Network for LiDAR and Camera-based 3D Object Detection in Outdoor Scenes](https://mlsanity.com/paper/2507.19304/) (2025)
- [StereoDETR: Stereo-based Transformer for 3D Object Detection](https://mlsanity.com/paper/2511.18788/) (2025)
- [Accurate and Real-time Pseudo Lidar Detection: Is Stereo Neural Network Really Necessary?](https://mlsanity.com/paper/2206.13858/) (2022)
- [Object-based SLAM utilizing unambiguous pose parameters considering general symmetry types](https://mlsanity.com/paper/2303.07872/) (2023)
- [Real-time Stereo-based 3D Object Detection for Streaming Perception](https://mlsanity.com/paper/2410.12394/) (2024)
- [Weak Cube R-CNN: Weakly Supervised 3D Detection using only 2D Bounding Boxes](https://mlsanity.com/paper/2504.13297/) (2025)
- [DDStereo: Efficient Dual Decoder Transformers for Stereo 3D Road Anomaly Detection](https://mlsanity.com/paper/2606.24805/) (2026)
- [Scalable Vision-Based 3D Object Detection and Monocular Depth Estimation for Autonomous Driving](https://mlsanity.com/paper/2403.02037/) (2024)

## Abstract (arXiv)

Safe autonomous driving requires reliable 3D object detection-determining the 6 DoF pose and dimensions of objects of interest. Using stereo cameras to solve this task is a cost-effective alternative to the widely used LiDAR sensor. The current state-of-the-art for stereo 3D object detection takes the existing PSMNet stereo matching network, with no modifications, and converts the estimated disparities into a 3D point cloud, and feeds this point cloud into a LiDAR-based 3D object detector. The issue with existing stereo matching networks is that they are designed for disparity estimation, not 3D object detection; the shape and accuracy of object point clouds are not the focus. Stereo matching networks commonly suffer from inaccurate depth estimates at object boundaries, which we define as streaking, because background and foreground points are jointly estimated. Existing networks also penalize disparity instead of the estimated position of object point clouds in their loss functions. We propose a novel 2D box association and object-centric stereo matching method that only estimates the disparities of the objects of interest to address these two issues. Our method achieves state-of-the-art results on the KITTI 3D and BEV benchmarks.