https://github.com/kentaroy47/point-cloud-neural-networks

Study works using point cloud+neural networks
https://github.com/kentaroy47/point-cloud-neural-networks

Last synced: 5 days ago
JSON representation

Study works using point cloud+neural networks

• Host: GitHub
• URL: https://github.com/kentaroy47/point-cloud-neural-networks
• Owner: kentaroy47
• Created: 2019-02-25T06:39:03.000Z (almost 6 years ago)
• Default Branch: master
• Last Pushed: 2019-02-25T07:30:44.000Z (almost 6 years ago)
• Last Synced: 2025-01-20T23:52:39.145Z (12 days ago)
• Size: 7.81 KB
• Stars: 1
• Watchers: 2
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
# Point-Cloud-Neural-Networks

Works using point cloud and neural networks.

## Point cloud CNN.

### CVPR 2017

[PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation](https://arxiv.org/abs/1612.00593)

Authors: Charles R. Qi, Hao Su, Kaichun Mo, Leonidas J. Guibas

Classification, segmentation.

### NIPS 2017.

[PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space](https://arxiv.org/abs/1706.02413)

Authors: Charles R. Qi, Li Yi, Hao Su, Leonidas J. Guibas

### CVPR 2018.

[So-net: Self-organizing network for point cloud analysis](http://openaccess.thecvf.com/content_cvpr_2018/html/Li_SO-Net_Self-Organizing_Network_CVPR_2018_paper.html)

Authors: J Li, BM Chen, G Hee Lee

[PointFusion: Deep Sensor Fusion for 3D Bounding Box Estimation](http://openaccess.thecvf.com/content_cvpr_2018/html/Xu_PointFusion_Deep_Sensor_CVPR_2018_paper.html)

Authors: Danfei Xu, Dragomir Anguelov, Ashesh Jain;

[Pointwise convolutional neural networks](http://openaccess.thecvf.com/content_cvpr_2018/html/Hua_Pointwise_Convolutional_Neural_CVPR_2018_paper.html)

Authors: BS Hua, MK Tran, SK Yeung

[Neural 3d mesh renderer](http://openaccess.thecvf.com/content_cvpr_2018/html/Kato_Neural_3D_Mesh_CVPR_2018_paper.html)

Authors: H Kato, Y Ushiku, T Harada

### ICRA 2018.

[SqueezeSeg: Convolutional Neural Nets with Recurrent CRF for Real-Time Road-Object Segmentation from 3D LiDAR Point Cloud](https://arxiv.org/abs/1710.07368)

### arXiv

## LiDAR-Camera Fusion

[Frustum pointnets for 3d object detection from rgb-d data](http://openaccess.thecvf.com/content_cvpr_2018/html/Qi_Frustum_PointNets_for_CVPR_2018_paper.html)

Authors: CR Qi, W Liu, C Wu, H Su, Leonidas J. Guibas

## Bird-view approach

・[Slideshare](https://www.slideshare.net/takmin/20181130-lidar-object-detection-survey)

・[Pixor: Real-time 3d object detection from point clouds](http://openaccess.thecvf.com/content_cvpr_2018/html/Yang_PIXOR_Real-Time_3D_CVPR_2018_paper.html)

Authors: B Yang, W Luo, R Urtasun, CVPR2018.

・点群を地面と平行にスライスし、各点群を画像チャネルとしてCNNへ入力。

・[Fusing bird view lidar point cloud and front view camera image for deep object detection](https://arxiv.org/abs/1711.06703)

Authors: Z Wang, W Zhan, M Tomizuka (Not really point cloud NN, but interesting approach.)

[Complex-YOLO: An Euler-Region-Proposal for Real-Time 3D Object Detection on Point Clouds](https://link.springer.com/chapter/10.1007/978-3-030-11009-3_11)

Authors: M Simon, S Milz, K Amende, HM Gross, ECCV 2018.

## Graph Convolution

[Dynamic graph cnn for learning on point clouds](https://arxiv.org/abs/1801.07829)

Authors: Y Wang, Y Sun, Z Liu, SE Sarma, MM Bronstein

## Voxel approach

[Voxelnet: End-to-end learning for point cloud based 3d object detection](http://openaccess.thecvf.com/content_cvpr_2018/html/Zhou_VoxelNet_End-to-End_Learning_CVPR_2018_paper.html)

Authors: Y Zhou, O Tuzel, CVPR2018.

## Others

[Pedestrian-Detection Method based on 1D-CNN during LiDAR Rotation](https://ieeexplore.ieee.org/abstract/document/8569014)

Authors: Yuki Kunisada ; Takayoshi Yamashita ; Hironobu Fujiyoshi, ICTS.

### slideshare

[CVPR2018のPointCloudのCNN論文とSPLATNet](https://www.slideshare.net/takmin/cvpr2018pointcloudcnnsplatnet)

## TBD

add technical points to each work.