# Structure Aware and Class Balanced 3D Object Detection on nuScenes Dataset

arXiv: https://arxiv.org/abs/2205.12519 · HTML: https://mlsanity.com/paper/2205.12519/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 15 of its 22 references that are in the map.
- First posted on arXiv 25 May 2022.

## Builds on (most cited first, 15 of 15)

- [nuScenes: A multimodal dataset for autonomous driving](https://mlsanity.com/paper/1903.11027/) (2019)
- [PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space](https://mlsanity.com/paper/1706.02413/) (2017)
- [Scalability in Perception for Autonomous Driving: Waymo Open Dataset](https://mlsanity.com/paper/1912.04838/) (2019)
- [Decoupled Weight Decay Regularization](https://mlsanity.com/paper/1711.05101/) (2017)
- [PointPillars: Fast Encoders for Object Detection from Point Clouds](https://mlsanity.com/paper/1812.05784/) (2018)
- [VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detection](https://mlsanity.com/paper/1711.06396/) (2017)
- [PIXOR: Real-time 3D Object Detection from Point Clouds](https://mlsanity.com/paper/1902.06326/) (2019)
- [Class-balanced Grouping and Sampling for Point Cloud 3D Object Detection](https://mlsanity.com/paper/1908.09492/) (2019)
- [Deep Continuous Fusion for Multi-Sensor 3D Object Detection](https://mlsanity.com/paper/2012.10992/) (2020)
- [Multi-Task Multi-Sensor Fusion for 3D Object Detection](https://mlsanity.com/paper/2012.12397/) (2020)
- [Deep Sliding Shapes for Amodal 3D Object Detection in RGB-D Images](https://mlsanity.com/paper/1511.02300/) (2015)
- [HDNET: Exploiting HD Maps for 3D Object Detection](https://mlsanity.com/paper/2012.11704/) (2020)
- [No Blind Spots: Full-Surround Multi-Object Tracking for Autonomous Vehicles using Cameras & LiDARs](https://mlsanity.com/paper/1802.08755/) (2018)
- [Ground Plane Polling for 6DoF Pose Estimation of Objects on the Road](https://mlsanity.com/paper/1811.06666/) (2018)
- [A Multimodal, Full-Surround Vehicular Testbed for Naturalistic Studies and Benchmarking: Design, Calibration and Deployment](https://mlsanity.com/paper/1709.07502/) (2017)

## Abstract (arXiv)

3-D object detection is pivotal for autonomous driving. Point cloud based methods have become increasingly popular for 3-D object detection, owing to their accurate depth information. NuTonomy's nuScenes dataset greatly extends commonly used datasets such as KITTI in size, sensor modalities, categories, and annotation numbers. However, it suffers from severe class imbalance. The Class-balanced Grouping and Sampling paper addresses this issue and suggests augmentation and sampling strategy. However, the localization precision of this model is affected by the loss of spatial information in the downscaled feature maps. We propose to enhance the performance of the CBGS model by designing an auxiliary network, that makes full use of the structure information of the 3D point cloud, in order to improve the localization accuracy. The detachable auxiliary network is jointly optimized by two point-level supervisions, namely foreground segmentation and center estimation. The auxiliary network does not introduce any extra computation during inference, since it can be detached at test time.