# Patch Refinement -- Localized 3D Object Detection

arXiv: https://arxiv.org/abs/1910.04093 · HTML: https://mlsanity.com/paper/1910.04093/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 9 Oct 2019.

## Built on by (most cited first, 7 of 7)

- [Voxel Transformer for 3D Object Detection](https://mlsanity.com/paper/2109.02497/) (2021)
- [Pyramid R-CNN: Towards Better Performance and Adaptability for 3D Object Detection](https://mlsanity.com/paper/2109.02499/) (2021)
- [AGO-Net: Association-Guided 3D Point Cloud Object Detection Network](https://mlsanity.com/paper/2208.11658/) (2022)
- [ImpDet: Exploring Implicit Fields for 3D Object Detection](https://mlsanity.com/paper/2203.17240/) (2022)
- [Survey and Systematization of 3D Object Detection Models and Methods](https://mlsanity.com/paper/2201.09354/) (2022)
- [Navigating Threats: A Survey of Physical Adversarial Attacks on LiDAR Perception Systems in Autonomous Vehicles](https://mlsanity.com/paper/2409.20426/) (2024)
- [DR.CPO: Diversified and Realistic 3D Augmentation via Iterative Construction, Random Placement, and HPR Occlusion](https://mlsanity.com/paper/2303.12743/) (2023)

## Abstract (arXiv)

We introduce Patch Refinement a two-stage model for accurate 3D object detection and localization from point cloud data. Patch Refinement is composed of two independently trained Voxelnet-based networks, a Region Proposal Network (RPN) and a Local Refinement Network (LRN). We decompose the detection task into a preliminary Bird's Eye View (BEV) detection step and a local 3D detection step. Based on the proposed BEV locations by the RPN, we extract small point cloud subsets ("patches"), which are then processed by the LRN, which is less limited by memory constraints due to the small area of each patch. Therefore, we can apply encoding with a higher voxel resolution locally. The independence of the LRN enables the use of additional augmentation techniques and allows for an efficient, regression focused training as it uses only a small fraction of each scene. Evaluated on the KITTI 3D object detection benchmark, our submission from January 28, 2019, outperformed all previous entries on all three difficulties of the class car, using only 50 % of the available training data and only LiDAR information.