机械臂6D姿态检测(RGB、RGBD、雷达)综述

1、单目:

(1)GDR-Net: Geometry-Guided Direct Regression Network for Monocular 6D Object Pose Estimation (GDR-Net:用于单目6D物体姿态估计的几何引导直接回归网络)

(2)Self-supervised 6D Object Pose Estimation for Robot Manipulation(机器人操纵的自监督6D物体姿态估计)

(3)Region Pixel Voting Network (RPVNet) for 6D Pose Estimation from Monocular Image(单目图像6D姿态估计的区域像素投票网络RPVNet)

(4)End-to-End 6DoF Pose Estimation From Monocular RGB Images(单目RGB图像的端到端6DoF姿态估计)

(5)Self6D: Self-Supervised Monocular 6D Object Pose Estimation(Self6D:自监督单眼6D物体姿态估计)

(6)Occlusion-Aware Self-Supervised Monocular 6D Object Pose Estimation(遮挡感知自监督单眼6D物体姿态估计)

(7)CPS++: Improving Class-level 6D Pose and Shape Estimation From Monocular Images With Self-Supervised Learning (CPS++:利用自监督学习改进单目图像的类级6D姿态和形状估计)

2、RGBD:

(1)Robust 6D Object Pose Estimation by Learning RGB-D Features(基于RGB-D特征的鲁棒6D目标姿态估计)

(2)DenseFusion: 6D Object Pose Estimation by Iterative Dense Fusion (DenseFusion:基于迭代密集融合的6D目标姿态估计)

扫描二维码关注公众号,回复: 16937434 查看本文章

(3)Texture-less object detection and 6D pose estimation in RGB-D images (RGB-D图像中的无纹理目标检测和6D姿态估计)

(4)Multi-view 6D Object Pose Estimation and Camera Motion Planning using RGBD Images(使用RGBD图像的多视图6D对象姿态估计和相机运动规划)

(5)Learning 6D Pose Estimation from Synthetic RGBD Images for Robotic Applications(用于机器人应用的合成RGBD图像学习6D姿态估计)

3、红外热成像:

(1)Semantic Segmentation for Thermal Images: A Comparative Survey(热图像语义分割的比较研究)

(2)A Generative Adversarial Network for Infrared and Visible Image Fusion Based on Semantic Segmentation(基于语义分割的红外可见图像融合生成对抗网络)

(3)ARTSeg: Employing Attention for Thermal images Semantic Segmentation(ARTSeg:关注热图像语义分割)

(4)MS-UDA: Multi-Spectral Unsupervised Domain Adaptation for Thermal Image Semantic Segmentation(MS-UDA:用于热图像语义分割的多光谱无监督域自适应)

4、激光雷达:

(1)ECPC-ICP: A 6D Vehicle Pose Estimation Method by Fusing the Roadside Lidar Point Cloud and Road Feature(ECPC-ICP:一种融合路边激光雷达点云和道路特征的6D车辆姿态估计方法)

(2)PointRCNN: 3D Object Proposal Generation and Detection from Point Cloud(PointRCNN:从点云生成和检测3D对象建议)

 (3)PV-RCNN: Point-Voxel Feature Set Abstraction for 3D Object Detection(PV-RCNN:用于3D对象检测的点体素特征集抽象)

(4)PointPillars: Fast Encoders for Object Detection from Point Clouds(PointPillars:用于点云目标检测的快速编码器)

5、混合:

(1)CL3D: Camera-LiDAR 3D Object Detection With Point Feature Enhancement and Point-Guided Fusion(CL3D:具有点特征增强和点引导融合的摄像机LiDAR 3D目标检测)

(2)CLOCs: Camera-LiDAR Object Candidates Fusion for 3D Object Detection(CLOC:用于3D目标检测的摄像机LiDAR目标候选融合)

(3)CramNet: Camera-Radar Fusion with Ray-Constrained Cross-Attention for Robust 3D Object Detection(CramNet:基于光线约束交叉关注的相机-雷达融合用于鲁棒三维目标检测)


1、单目:

(1)GDR-Net: Geometry-Guided Direct Regression Network for Monocular 6D Object Pose Estimation (GDR-Net:用于单目6D物体姿态估计的几何引导直接回归网络)

https://openaccess.thecvf.com/content/CVPR2021/papers/Wang_GDR-Net_Geometry-Guided_Direct_Regression_Network_for_Monocular_6D_Object_Pose_CVPR_2021_paper.pdf

(2)Self-supervised 6D Object Pose Estimation for Robot Manipulation(机器人操纵的自监督6D物体姿态估计)

https://arxiv.org/pdf/1909.10159.pdf

(3)Region Pixel Voting Network (RPVNet) for 6D Pose Estimation from Monocular Image(单目图像6D姿态估计的区域像素投票网络RPVNet)

Region Pixel Voting Network (RPVNet) for 6D Pose Estimation from Monocular Image

(4)End-to-End 6DoF Pose Estimation From Monocular RGB Images(单目RGB图像的端到端6DoF姿态估计)

End-to-End 6DoF Pose Estimation From Monocular RGB Images | IEEE Journals & Magazine | IEEE Xplore

(5)Self6D: Self-Supervised Monocular 6D Object Pose Estimation(Self6D:自监督单眼6D物体姿态估计)

https://arxiv.org/pdf/2004.06468.pdf

(6)Occlusion-Aware Self-Supervised Monocular 6D Object Pose Estimation(遮挡感知自监督单眼6D物体姿态估计)

https://arxiv.org/pdf/2203.10339.pdf

(7)CPS++: Improving Class-level 6D Pose and Shape Estimation From Monocular Images With Self-Supervised Learning (CPS++:利用自监督学习改进单目图像的类级6D姿态和形状估计)

https://arxiv.org/pdf/2003.05848.pdf

2、RGBD:

(1)Robust 6D Object Pose Estimation by Learning RGB-D Features(基于RGB-D特征的鲁棒6D目标姿态估计)

https://arxiv.org/pdf/2003.00188.pdf

(2)DenseFusion: 6D Object Pose Estimation by Iterative Dense Fusion (DenseFusion:基于迭代密集融合的6D目标姿态估计)

https://openaccess.thecvf.com/content_CVPR_2019/papers/Wang_DenseFusion_6D_Object_Pose_Estimation_by_Iterative_Dense_Fusion_CVPR_2019_paper.pdf

(3)Texture-less object detection and 6D pose estimation in RGB-D images (RGB-D图像中的无纹理目标检测和6D姿态估计)

https://www.sciencedirect.com/science/article/abs/pii/S0921889016308442

直接查看链接:Sci-Hub | Texture-less object detection and 6D pose estimation in RGB-D images | 10.1016/j.robot.2017.06.003

(4)Multi-view 6D Object Pose Estimation and Camera Motion Planning using RGBD Images(使用RGBD图像的多视图6D对象姿态估计和相机运动规划)

https://openaccess.thecvf.com/content_ICCV_2017_workshops/papers/w31/Sock_Multi-View_6D_Object_ICCV_2017_paper.pdf

(5)Learning 6D Pose Estimation from Synthetic RGBD Images for Robotic Applications(用于机器人应用的合成RGBD图像学习6D姿态估计)

https://arxiv.org/pdf/2208.14288.pdf

3、红外热成像:

(1)Semantic Segmentation for Thermal Images: A Comparative Survey(热图像语义分割的比较研究)

https://openaccess.thecvf.com/content/CVPR2022W/PBVS/papers/Kutuk_Semantic_Segmentation_for_Thermal_Images_A_Comparative_Survey_CVPRW_2022_paper.pdf

(2)A Generative Adversarial Network for Infrared and Visible Image Fusion Based on Semantic Segmentation(基于语义分割的红外可见图像融合生成对抗网络)

Entropy | Free Full-Text | A Generative Adversarial Network for Infrared and Visible Image Fusion Based on Semantic Segmentation

(3)ARTSeg: Employing Attention for Thermal images Semantic Segmentation(ARTSeg:关注热图像语义分割)

https://arxiv.org/pdf/2111.15257.pdf

(4)MS-UDA: Multi-Spectral Unsupervised Domain Adaptation for Thermal Image Semantic Segmentation(MS-UDA:用于热图像语义分割的多光谱无监督域自适应)

MS-UDA: Multi-Spectral Unsupervised Domain Adaptation for Thermal Image Semantic Segmentation | IEEE Journals & Magazine | IEEE Xplore


4、激光雷达:

(1)ECPC-ICP: A 6D Vehicle Pose Estimation Method by Fusing the Roadside Lidar Point Cloud and Road Feature(ECPC-ICP:一种融合路边激光雷达点云和道路特征的6D车辆姿态估计方法)

Sensors | Free Full-Text | ECPC-ICP: A 6D Vehicle Pose Estimation Method by Fusing the Roadside Lidar Point Cloud and Road Feature

(2)PointRCNN: 3D Object Proposal Generation and Detection from Point Cloud(PointRCNN:从点云生成和检测3D对象建议)

https://openaccess.thecvf.com/content_CVPR_2019/papers/Shi_PointRCNN_3D_Object_Proposal_Generation_and_Detection_From_Point_Cloud_CVPR_2019_paper.pdf

 (3)PV-RCNN: Point-Voxel Feature Set Abstraction for 3D Object Detection(PV-RCNN:用于3D对象检测的点体素特征集抽象)

https://openaccess.thecvf.com/content_CVPR_2020/papers/Shi_PV-RCNN_Point-Voxel_Feature_Set_Abstraction_for_3D_Object_Detection_CVPR_2020_paper.pdf

(4)PointPillars: Fast Encoders for Object Detection from Point Clouds(PointPillars:用于点云目标检测的快速编码器)

https://openaccess.thecvf.com/content_CVPR_2019/papers/Lang_PointPillars_Fast_Encoders_for_Object_Detection_From_Point_Clouds_CVPR_2019_paper.pdf


5、混合:

(1)CL3D: Camera-LiDAR 3D Object Detection With Point Feature Enhancement and Point-Guided Fusion(CL3D:具有点特征增强和点引导融合的摄像机LiDAR 3D目标检测)

https://eprints.gla.ac.uk/266475/2/266475.pdf

(2)CLOCs: Camera-LiDAR Object Candidates Fusion for 3D Object Detection(CLOC:用于3D目标检测的摄像机LiDAR目标候选融合)

https://arxiv.org/pdf/2009.00784.pdf

(3)CramNet: Camera-Radar Fusion with Ray-Constrained Cross-Attention for Robust 3D Object Detection(CramNet:基于光线约束交叉关注的相机-雷达融合用于鲁棒三维目标检测)

https://arxiv.org/pdf/2210.09267.pdf

猜你喜欢

转载自blog.csdn.net/Callme_TeacherPi/article/details/128205823
今日推荐