딥러닝 기반 3차원 객체 인식

이 글은 딥러닝 기반 3차원 객체를 인식하는 방법들을 간단히 조사해 정리한다.

PointRCNN

PointRCNN(Shaoshuai Shi, 2019)

PointSIFT

PointSIFT(Mingyang Jiang, 2018)

Votenet

Votenet(Charles R. Qi, 2019) (Version #2)

Superpoint graph

Superpoint graph(Loic Landrieu, 2018)

Complex-YOLO

Complex-YOLO(Liu, 2018)

Semantic3dnet

Semantic3dnet(hackel, 2017)

LiDAR-Bonnetal

LiDAR-Bonnetal(Andres Milioto, 2019)

JSIS3D

JSIS3D(Quang-Hieu Pham, 2019)

3D point cloud generation

3D point cloud generation(Chen-Hsuan Lin, 2018)

Multiple object tracking lidar

Multiple object tracking lidar(Praveen palanisamy, 2015)

OpenDetection

Open detection(Kripasindhu Sarkar, 2015)

레퍼런스

• Shaoshuai Shi, 2019, PointRCNN for 3D Object Detection from Raw Point Cloud, CVPR 2019
• Mingyang Jiang, 2018, PointSIFT: 3D semantic segmentation in point clouds
• Charles R. Qi, 2019, Deep Hough Voting for 3D Object Detection in Point Clouds, facebook research
• Loic Landrieu, 2018, Large-scale Point Cloud Semantic Segmentation with Superpoint Graphs
• Liu, 2018, Complex-YOLO: Real-time 3D Object Detection on Point Clouds pytorch Darknet
• Hackel, 2017, Point cloud semantic segmentation via Deep 3D Convolutional Neural Network
• Andres Milioto, 2019, Semantic Segmentation of point clouds using range images
• Quang-Hieu Pham, 2019, JSIS3D: Joint Semantic-Instance Segmentation of 3D Point Clouds
• Chen-Hsuan Lin, 2018, Learning Efficient Point Cloud Generation for Dense 3D Object Reconstruction
• Praveen palanisamy, 2015, Detect, track and classify multiple objects using LIDAR scans or point cloud
• Kripasindhu Sarkar, 2015, object detection and recognition in images and 3D point clouds