1.YOLO3D2.SSD-6D3.3D Bounding Box Estimation Using Deep Learning and Geometry4.GS3D:An Effcient 3D Object Detection Framework for Autonomous Driving5.Deep MANTA: A Coarse-to-fine Many-Task Network for joint 2D and 3D vehicle analysis from monocular image6.Task-Aware Monocular Depth Estimation for 3D Object Detection7.M3D-RPN: Monocular 3D Region Proposal Network for Object Detection8.Monocular 3D Object Detection with Pseudo-LiDAR Point Cloud9.Monocular 3D Object Detection and Box Fitting Trained End-to-End Using Intersection-over-Union Loss10.Disentangling Monocular 3D Object Detection11.Shift R-CNN: Deep Monocular 3d Object Detection With Closed-Form Geometric Constraints12.Monocular 3D Object Detection via Geometric Reasoning on Keypoints13.Monocular 3D Object Detection Leveraging Accurate Proposals and Shape Reconstruction14.Accurate Monocular Object Detection via Color-Embedded 3D Reconstruction for Autonomous Driving15.3D Bounding Boxes for Road Vehicles: A One-Stage, Localization Prioritized Approach using Single Monocular Images16.Orthographic Feature Transform for Monocular 3D Object Detection17.Multi-Level Fusion based 3D Object Detection from Monocular Images18.MonoGRNet:A Geometric Reasoning Network for Monocular 3D Object Localization19.Mono3D++: Monocular 3D Vehicle Detection with Two-Scale 3D Hypotheses and Task Priors
2、 基于激光雷达点云的3D物体检测
1.VoteNet2.End-to-End Multi-View Fusion for 3D Object Detection in LiDAR Point Clouds3.Deep Hough Voting for 3D Object Detection in Point Clouds4.STD: Sparse-to-Dense 3D Object Detector for Point Cloud5.PointPillars: Fast Encoders for Object Detection from Point Clouds6.PointRCNN: 3D Object Proposal Generation and Detection from Point Cloud7.PIXOR: Real-time 3D Object Detection from Point Clouds8.Complex-YOLO: An Euler-Region-Proposal for Real-time 3D Object Detection on Point Clouds9.YOLO3D: End-to-end real-time 3D Oriented Object Bounding Box Detection from LiDAR Point Cloud10.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 Networks12.RT3D: Real-Time 3-D Vehicle Detection in LiDAR Point Cloud for Autonomous Driving13.BirdNet: a 3D Object Detection Framework from LiDAR information14.IPOD: Intensive Point-based Object Detector for Point Cloud15.PIXOR: Real-time 3D Object Detection from Point Clouds16.DepthCN: Vehicle Detection Using 3D-LIDAR and ConvNet17.YOLO4D: A ST Approach for RT Multi-object Detection and Classification from LiDAR Point Clouds18.PointRCNN: 3D Object Proposal Generation and Detection from Point Cloud19.Part-A^2 Net: 3D Part-Aware and Aggregation Neural Network for Object Detection from Point Cloud20.Voxel-FPN: multi-scale voxel feature aggregation in 3D object detection from point clouds21.Fast Point RCNN22.StarNet: Targeted Computation for Object Detection in Point Clouds23.Class-balanced Grouping and Sampling for Point Cloud 3D Object Detection24.LaserNet: An Efficient Probabilistic 3D Object Detector for Autonomous Driving
3、 基于RGB-D图像的3D物体检测
1.Frustum PointNets for 3D Object Detection from RGB-D Data2.Frustum VoxNet for 3D object detection from RGB-D or Depth images
4、 基于融合方法的3D物体检测(RGB图像+激光雷达/深度图)
1.AVOD2.A General Pipeline for 3D Detection of Vehicles3.Adaptive and Azimuth-Aware Fusion Network of Multimodal Local Features for 3D Object Detection4.Deep Continuous Fusion for Multi-Sensor 3D Object Detection5.Frustum PointNets for 3D Object Detection from RGB-D Data6.Joint 3D Proposal Generation and Object Detection from View Aggregation7.Multi-Task Multi-Sensor Fusion for 3D Object Detection8.Multi-View 3D Object Detection Network for Autonomous Driving9.PointFusion:Deep Sensor Fusion for 3D Bounding Box Estimation10.Pseudo-LiDAR from Visual Depth Estimation:Bridging the Gap in 3D Object Detection for Autonomous Driving
5、 基于双目视觉下的3D物体检测
1.Object-Centric Stereo Matching for 3D Object Detection2.Triangulation Learning Network: from Monocular to Stereo 3D Object Detection3.Pseudo-LiDAR from Visual Depth Estimation: Bridging the Gap in 3D Object Detection for Autonomous Driving4.Stereo R-CNN based 3D Object Detection for Autonomous Driving
6、单目图像深度图生成
1.Deep Ordinal Regression Network for Monocular Depth Estimation2.Depth from Videos in the Wild: Unsupervised Monocular Depth Learning from Unknown Cameras3.Detail Preserving Depth Estimation from a Single Image Using Attention Guided Networks4.FastDepth: Fast Monocular Depth Estimation on Embedded Systems5.Single View Stereo Matching
7、单目图像+激光雷达点云深度图生成
1.Sparse and noisy LiDAR completion with RGB guidance and uncertainty2.Learning Guided Convolutional Network for Depth Completion3.DFineNet: Ego-Motion Estimation and Depth Refinement from Sparse, Noisy Depth Input with RGB Guidance
8、深度图补全
1.Deep RGB-D Canonical Correlation Analysis For Sparse Depth Completion2.Sparse and noisy LiDAR completion with RGB guidance and uncertainty3.Confidence Propagation through CNNs for Guided Sparse Depth Regression4.Learning Guided Convolutional Network for Depth Completion5.DFineNet: Ego-Motion Estimation and Depth Refinement from Sparse, Noisy Depth Input with RGB Guidance6.Depth Completion from Sparse LiDAR Data with Depth-Normal Constraints
(十一)三维重建
学习书籍
1.Computer Vision for Visual Effects2.Computer Vision Algorithms and Applications
相关论文
1.Rolling Shutter Pose and Ego-motion Estimation using Shape-from-Template(ECCV2018)2.BundleFusion: Real-time Globally Consistent 3D Reconstruction using On-the-fly Surface Re-integration(ACM)3.Depth Map Prediction from a Single Image using a Multi-Scale Deep Network4.3D-R2N2:A Unified Approach for Single and Multi-view 3D Object Reconstruction 5.Pixel2Mesh:Generating 3D Mesh Models form Single RGB Images6.Mesh R-CNN(FAIR,CVPR2019)7.Conditional Single-view Shape Generation for Multi-view Stereo Reconstruction8.R-MVSNet: Recurrent MVSNet for High-resolution Multi-view Stereo Depth Inference9.StereoDRNet: Dilated Residual Stereo Net(cvpr2019)
一些开源网站
1. Malaga Dataset2. Tum: Computer Vision Lab: RGB-D3. KITTI Dataset4. University of Freiburg: Department of Computer Science5. MRPT6. ICDL-NUIM
SLAM学习书籍
概率机器人
视觉SLAM十四讲
计算机视觉中的多视图几何
机器人学中的状态估计
Principles of Robot Motion Theory,Algorithms and Implementation