• Corpus ID: 238582916

3D Object Detection Combining Semantic and Geometric Features from Point Clouds

@article{Peng20213DOD,
  title={3D Object Detection Combining Semantic and Geometric Features from Point Clouds},
  author={Hao Peng and Guofeng Tong and Zheng Li and Yaqi Wang and Yu-Ruei Shao},
  journal={ArXiv},
  year={2021},
  volume={abs/2110.04704}
}
In this paper, we investigate the combination of voxel-based methods and point-based methods, and propose a novel end-toend two-stage 3D object detector named SGNet for point clouds scenes. The voxel-based methods voxelize the scene to regular grids, which can be processed with the current advanced feature learning frameworks based on convolutional layers for semantic feature learning. Whereas the point-based methods can better extract the geometric feature of the point due to the coordinate… 

Figures and Tables from this paper

References

SHOWING 1-10 OF 38 REFERENCES

PointRCNN: 3D Object Proposal Generation and Detection From Point Cloud

Extensive experiments on the 3D detection benchmark of KITTI dataset show that the proposed architecture outperforms state-of-the-art methods with remarkable margins by using only point cloud as input.

VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detection

  • Yin ZhouOncel Tuzel
  • Computer Science, Environmental Science
    2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition
  • 2018
VoxelNet is proposed, a generic 3D detection network that unifies feature extraction and bounding box prediction into a single stage, end-to-end trainable deep network and learns an effective discriminative representation of objects with various geometries, leading to encouraging results in3D detection of pedestrians and cyclists.

PV-RCNN: Point-Voxel Feature Set Abstraction for 3D Object Detection

The proposed PV-RCNN surpasses state-of-the-art 3D detection methods with remarkable margins and deeply integrates both 3D voxel Convolutional Neural Network and PointNet-based set abstraction to learn more discriminative point cloud features.

Voxel R-CNN: Towards High Performance Voxel-based 3D Object Detection

It is found that precise positioning of raw points is not essential for high performance 3D object detection and that the coarse voxel granularity can also offer sufficient detection accuracy, so Voxel R-CNN, a simple but effective voxEL-based framework, is devised.

STD: Sparse-to-Dense 3D Object Detector for Point Cloud

This work proposes a two-stage 3D object detection framework, named sparse-to-dense 3D Object Detector (STD), and implements a parallel intersection-over-union (IoU) branch to increase awareness of localization accuracy, resulting in further improved performance.

EPNet: Enhancing Point Features with Image Semantics for 3D Object Detection

A novel fusion module is proposed to enhance the point features with semantic image features in a point-wise manner without any image annotations to address two critical issues in the 3D detection task, including the exploitation of multiple sensors~ and the inconsistency between the localization and classification confidence.

3D IoU-Net: IoU Guided 3D Object Detector for Point Clouds

A 3D IoU prediction branch is added to the regular classification and regression branches and the IoU alignment operation is introduced to resolve the mismatching between the bounding box regression head and IoU Prediction, thereby further enhancing the accuracy of IoU predictions.

TANet: Robust 3D Object Detection from Point Clouds with Triple Attention

A novel TANet is introduced in this paper, which mainly contains a Triple Attention (TA) module, and a Coarse-to-Fine Regression (CFR) module that boosts the accuracy of localization without excessive computation cost.