3D目标检测论文汇总

一、单目图像下的3D目标检测

1、YOLO3D

2、SSD-6D

3、3D Bounding Box Estimation Using Deep Learning and Geometry

4、GS3D:An Effcient 3D Object Detection Framework for Autonomous Driving

5、Deep MANTA: A Coarse-to-fine Many-Task Network for joint 2D and 3D vehicle analysis from monocular image

6、Task-Aware Monocular Depth Estimation for 3D Object Detection

7、M3D-RPN: Monocular 3D Region Proposal Network for Object Detection

8、Monocular 3D Object Detection with Pseudo-LiDAR Point Cloud

9、Monocular 3D Object Detection and Box Fitting Trained End-to-End Using Intersection-over-Union Loss

10、Disentangling Monocular 3D Object Detection

11、Shift R-CNN: Deep Monocular 3d Object Detection With Closed-Form Geometric Constraints

12、Monocular 3D Object Detection via Geometric Reasoning on Keypoints

13、Monocular 3D Object Detection Leveraging Accurate Proposals and Shape Reconstruction

14、Accurate Monocular Object Detection via Color-Embedded 3D Reconstruction for Autonomous Driving

15、3D Bounding Boxes for Road Vehicles: A One-Stage, Localization Prioritized Approach using Single Monocular Images

16、Orthographic Feature Transform for Monocular 3D Object Detection

17、Multi-Level Fusion based 3D Object Detection from Monocular Images

18、MonoGRNet: A Geometric Reasoning Network for Monocular 3D Object Localization

19、Mono3D++: Monocular 3D Vehicle Detection with Two-Scale 3D Hypotheses and Task Priors

二、基于融合的方法RGB图像+激光雷达/深度图的3D目标检测

1、AVOD

2、A General Pipeline for 3D Detection of Vehicles

3、Adaptive and Azimuth-Aware Fusion Network of Multimodal Local Features for 3D Object Detection

4、Deep Continuous Fusion for Multi-Sensor 3D Object Detection

5、Frustum PointNets for 3D Object Detection from RGB-D Data

6、Joint 3D Proposal Generation and Object Detection from View Aggregation

7、Multi-Task Multi-Sensor Fusion for 3D Object Detection

8、Multi-View 3D Object Detection Network for Autonomous Driving

9、PointFusion：Deep Sensor Fusion for 3D Bounding Box Estimation

10、Pseudo-LiDAR from Visual Depth Estimation：Bridging the Gap in 3D Object Detection for Autonomous Driving

三、基于激光雷达点云的3D目标检测

1、VoteNet

2、End-to-End Multi-View Fusion for 3D Object Detection in LiDAR Point Clouds

3、Deep Hough Voting for 3D Object Detection in Point Clouds

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

5、PointPillars: Fast Encoders for Object Detection from Point Clouds

6、PointRCNN: 3D Object Proposal Generation and Detection from Point Cloud

7、PIXOR: Real-time 3D Object Detection from Point Clouds

8、Complex-YOLO: An Euler-Region-Proposal for Real-time 3D Object Detection on Point Clouds

9、YOLO3D: End-to-end real-time 3D Oriented Object Bounding Box Detection from LiDAR Point Cloud

10、Vehicle Detection from 3D Lidar Using FCN（百度早期工作2016年）

11、Object Detection and Classification in Occupancy Grid Maps using Deep Convolutional Networks

12、RT3D: Real-Time 3-D Vehicle Detection in LiDAR Point Cloud for Autonomous Driving

13、BirdNet: a 3D Object Detection Framework from LiDAR information

14、IPOD: Intensive Point-based Object Detector for Point Cloud

15、PIXOR: Real-time 3D Object Detection from Point Clouds

16、DepthCN: Vehicle Detection Using 3D-LIDAR and ConvNet

17、YOLO4D: A ST Approach for RT Multi-object Detection and Classification from LiDAR Point Clouds

18、PointRCNN: 3D Object Proposal Generation and Detection from Point Cloud

19、Part-A^2 Net: 3D Part-Aware and Aggregation Neural Network for Object Detection from Point Cloud

20、Voxel-FPN: multi-scale voxel feature aggregation in 3D object detection from point clouds

21、Fast Point RCNN

22、StarNet: Targeted Computation for Object Detection in Point Clouds

23、Class-balanced Grouping and Sampling for Point Cloud 3D Object Detection

24、LaserNet: An Efficient Probabilistic 3D Object Detector for Autonomous Driving

四、基于RGB-D图像下的3D目标检测

1、Frustum PointNets for 3D Object Detection from RGB-D Data

2、Frustum VoxNet for 3D object detection from RGB-D or Depth images

五、基于立体视觉下的3D目标检测

1、Object-Centric Stereo Matching for 3D Object Detection

2、Triangulation Learning Network: from Monocular to Stereo 3D Object Detection

3、Pseudo-LiDAR from Visual Depth Estimation: Bridging the Gap in 3D Object Detection for Autonomous Driving

4、Stereo R-CNN based 3D Object Detection for Autonomous Driving