# 3D Object Proposals using Stereo Imagery for Accurate Object Class Detection

arXiv: https://arxiv.org/abs/1608.07711 · HTML: https://mlsanity.com/paper/1608.07711/

## Key facts

- Cited by 58 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 27 Aug 2016.

## Built on by (most cited first, 30 of 58)

- [3D Object Detection for Autonomous Driving: A Comprehensive Survey](https://mlsanity.com/paper/2206.09474/) (2022)
- [3D Object Detection for Autonomous Driving: A Survey](https://mlsanity.com/paper/2106.10823/) (2021)
- [Multi-modal Sensor Fusion for Auto Driving Perception: A Survey](https://mlsanity.com/paper/2202.02703/) (2022)
- [LIGA-Stereo: Learning LiDAR Geometry Aware Representations for Stereo-based 3D Detector](https://mlsanity.com/paper/2108.08258/) (2021)
- [Monocular 3D Object Detection: An Extrinsic Parameter Free Approach](https://mlsanity.com/paper/2106.15796/) (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)
- [Radar-Camera Fusion for Object Detection and Semantic Segmentation in Autonomous Driving: A Comprehensive Review](https://mlsanity.com/paper/2304.10410/) (2023)
- [Learning to Detect Mobile Objects from LiDAR Scans Without Labels](https://mlsanity.com/paper/2203.15882/) (2022)
- [M3DSSD: Monocular 3D Single Stage Object Detector](https://mlsanity.com/paper/2103.13164/) (2021)
- [DID-M3D: Decoupling Instance Depth for Monocular 3D Object Detection](https://mlsanity.com/paper/2207.08531/) (2022)
- [Learning Occupancy for Monocular 3D Object Detection](https://mlsanity.com/paper/2305.15694/) (2023)
- [MonoNeRD: NeRF-like Representations for Monocular 3D Object Detection](https://mlsanity.com/paper/2308.09421/) (2023)
- [Lidar Point Cloud Guided Monocular 3D Object Detection](https://mlsanity.com/paper/2104.09035/) (2021)
- [Homogeneous Multi-modal Feature Fusion and Interaction for 3D Object Detection](https://mlsanity.com/paper/2210.09615/) (2022)
- [Artificial Intelligence for the Metaverse: A Survey](https://mlsanity.com/paper/2202.10336/) (2022)
- [Evaluating Adversarial Attacks on Driving Safety in Vision-Based Autonomous Vehicles](https://mlsanity.com/paper/2108.02940/) (2021)
- [Act Like a Radiologist: Towards Reliable Multi-view Correspondence Reasoning for Mammogram Mass Detection](https://mlsanity.com/paper/2105.10160/) (2021)
- [OmniNOCS: A unified NOCS dataset and model for 3D lifting of 2D objects](https://mlsanity.com/paper/2407.08711/) (2024)
- [MonoGRNet: A General Framework for Monocular 3D Object Detection](https://mlsanity.com/paper/2104.08797/) (2021)
- [PLUMENet: Efficient 3D Object Detection from Stereo Images](https://mlsanity.com/paper/2101.06594/) (2021)
- [WeakM3D: Towards Weakly Supervised Monocular 3D Object Detection](https://mlsanity.com/paper/2203.08332/) (2022)
- [MonoATT: Online Monocular 3D Object Detection with Adaptive Token Transformer](https://mlsanity.com/paper/2303.13018/) (2023)
- [The Implicit Values of A Good Hand Shake: Handheld Multi-Frame Neural Depth Refinement](https://mlsanity.com/paper/2111.13738/) (2021)
- [SIDE: Center-based Stereo 3D Detector with Structure-aware Instance Depth Estimation](https://mlsanity.com/paper/2108.09663/) (2021)
- [Neighbor-Vote: Improving Monocular 3D Object Detection through Neighbor Distance Voting](https://mlsanity.com/paper/2107.02493/) (2021)
- [Gated3D: Monocular 3D Object Detection From Temporal Illumination Cues](https://mlsanity.com/paper/2102.03602/) (2021)
- [Stereo CenterNet based 3D Object Detection for Autonomous Driving](https://mlsanity.com/paper/2103.11071/) (2021)
- [DeepMix: Mobility-aware, Lightweight, and Hybrid 3D Object Detection for Headsets](https://mlsanity.com/paper/2201.08812/) (2022)
- [DSGN++: Exploiting Visual-Spatial Relation for Stereo-based 3D Detectors](https://mlsanity.com/paper/2204.03039/) (2022)

## Abstract (arXiv)

The goal of this paper is to perform 3D object detection in the context of autonomous driving. Our method first aims at generating a set of high-quality 3D object proposals by exploiting stereo imagery. We formulate the problem as minimizing an energy function that encodes object size priors, placement of objects on the ground plane as well as several depth informed features that reason about free space, point cloud densities and distance to the ground. We then exploit a CNN on top of these proposals to perform object detection. In particular, we employ a convolutional neural net (CNN) that exploits context and depth information to jointly regress to 3D bounding box coordinates and object pose. Our experiments show significant performance gains over existing RGB and RGB-D object proposal methods on the challenging KITTI benchmark. When combined with the CNN, our approach outperforms all existing results in object detection and orientation estimation tasks for all three KITTI object classes. Furthermore, we experiment also with the setting where LIDAR information is available, and show that using both LIDAR and stereo leads to the best result.