刚体6D位姿估计方法综述
https://zhuanlan.zhihu.com/p/143987243
G2L-Net
论文标题:G2L-Net: Global to Local Network for Real-time 6D Pose Estimation with Embedding Vector Features
论文来源:CVPR 2020
论文链接:https://arxiv.org/abs/2003.11089
代码链接:https://github.com/DC1991/G2L_Net
PVN3D
论文标题:PVN3D: A Deep Point-wise 3D Keypoints Voting Network for 6DoF Pose Estimation
论文来源:CVPR 2020
论文链接:https://arxiv.org/abs/1911.04231
代码链接:https://github.com/ethnhe/PVN3D
DPVL
论文标题:6DoF Object Pose Estimation via Differentiable Proxy Voting Loss
论文来源:CVPR 2020
论文链接:https://arxiv.org/abs/2002.03923
https://zhuanlan.zhihu.com/p/99803328
DenseFusion
论文标题:DenseFusion: 6D Object Pose Estimation by Iterative Dense Fusion (CVPR2019)
原文链接:https://arxiv.org/abs/1901.04780
代码链接:https://github.com/j96w/DenseFu
PVNet
论文标题:PVNet: Pixel-wise Voting Network for 6DoF Pose Estimation
论文链接:https://arxiv.org/pdf/1812.11788.pdf
代码链接:https://github.com/zju3dv/pvnet
论文标题:Normalized Object Coordinate Space for Category-Level 6D Object Pose and Size Estimation(CVPR2019)
论文链接:https://arxiv.org/abs/1901.02970
代码链接:https://github.com/hughw19/NOCS
论文标题:Pix2Pose: Pixel-Wise Coordinate Regression of Objects for 6D Pose Estimation(ICCV2019)
论文链接:https://arxiv.org/abs/1908.0743
论文标题:Deep-6DPose: Recovering 6D Object Pose from a Single RGB Image
论文链接:https://arxiv.org/abs/1802.1036
论文标题:Multi-Task Template Matching for Object Detection, Segmentation and Pose Estimation Using Depth Images(ICRA2019)
论文链接:https://ieeexplore.ieee.org/document/8794448
论文标题:Real-Time Seamless Single Shot 6D Object Pose Prediction(CVPR2018)
论文链接:https://arxiv.org/abs/1711.08848
代码链接:https://github.com/Microsoft/singleshotpose
论文标题:SSD-6D: Making RGB-Based 3D Detection and 6D Pose Estimation Great Again
论文链接:https://arxiv.org/abs/1711.10006v1
代码链接:https://github.com/wadimkehl/ssd-6d
https://mp.weixin.qq.com/s?__biz=MzU1MjY4MTA1MQ==&mid=2247484871&idx=1&sn=ba4749a133b8a456b5430e5d1ea96ace&chksm=fbff2ef3cc88a7e59e50dbb9239bbb4839cb608a2b36fa8fd39c29f38f03c17bdd606e81bd3b&scene=178&cur_album_id=1433707278687109122#rd
论文标题:PoseNet: A Convolutional Network for Real-Time 6-DOF Camera Relocalization
论文链接:https://arxiv.org/abs/1505.07427
代码链接:http://mi.eng.cam.ac.uk/projects/relocalisation/
论文标题:6-PACK: Category-level 6D Pose Tracker with Anchor-Based Keypoints
论文链接:https://arxiv.org/abs/1910.10750v1
代码链接:https://sites.google.com/view/6packtracking
论文标题:Multi-view 6D Object Pose Estimation and Camera Motion Planning using RGBD Images
论文链接:https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8265470
论文标题:Going further with point pair features
论文链接:http://arxiv.org/abs/1711.04061
论文标题:BOP: Benchmark for 6D Object Pose Estimation
论文链接:https://arxiv.org/abs/1808.08319
代码链接:https://bop.felk.cvut.cz/home/
论文标题:Multimodal Templates for Real-Time Detection of Texture-less Objects in Heavily Cluttered Scenes (ICCV), 2011.
论文链接:http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=6126326
论文标题:Gradient Response Maps for Real-Time Detection of Texture-Less Objects.
论文链接:https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6042881
论文标题:Model Based Training, Detection and Pose Estimation of Texture-Less 3D Objects in Heavily Cluttered Scenes.
论文链接:https://link.springer.com/content/pdf/10.1007%2F978-3-642-37331-2.pdf
ECCV 2020:
https://zhuanlan.zhihu.com/p/260787827
Self6D: Self-Supervised Monocular 6D Object Pose Estimation
作者 | Gu Wang, Fabian Manhardt, Jianzhun Shao, Xiangyang Ji, Nassir Navab, Federico Tombari
单位 | 清华大学;慕尼黑工业大学;谷歌
论文 | https://arxiv.org/abs/2004.06468
代码 | https://github.com/THU-DA-6D-Pose-Group/Self6D-Diff-Renderer
备注 | ECCV 2020 Oral
Neural Object Learning for 6D Pose Estimation Using a Few Cluttered Images
作者 | Kiru Park, Timothy Patten, Markus Vincze
单位 | TU Wien
论文 | https://arxiv.org/abs/2005.03717
代码 | https://github.com/kirumang/NOL
数据集 | https://www.acin.tuwien.ac.at/en/vision-for-robotics/software-tools/smot/
备注 | ECCV 2020 Spotlight
CosyPose: Consistent multi-view multi-object 6D pose estimation
多视角多物体6D姿态估计
作者 | Yann Labbé, Justin Carpentier, Mathieu Aubry, Josef Sivic
单位 | 巴黎文理研究大学又译巴黎科学人文艺术大学;INRIA等
论文 | https://arxiv.org/abs/2008.08465
代码 | https://github.com/ylabbe/cosypose
主页 | https://www.di.ens.fr/willow/research/cosypose/
备注 | ECCV 2020
Category Level Object Pose Estimation via Neural Analysis-by-Synthesis
作者 | Xu Chen, Zijian Dong, Jie Song, Andreas Geiger, Otmar Hilliges
单位 | 苏黎世联邦理工学院;图宾根大学等
论文 | https://arxiv.org/abs/2008.08145
主页 | https://ait.ethz.ch/projects/2020/neural-object-fitting/
备注 | ECCV 2020
Shape Prior Deformation for Categorical 6D Object Pose and Size Estimation
6D物体姿态和尺寸估计
作者 | Meng Tian, Marcelo H Ang Jr, Gim Hee Lee
单位 | 新加坡国立大学
论文 | https://arxiv.org/abs/2007.08454
代码 | https://github.com/mentian/object-deformnet
备注 | ECCV 2020
CVPR2020
https://zhuanlan.zhihu.com/p/148742530
HybridPose: 6D Object Pose Estimation under Hybrid Representations
标题:HybridPose: 混合表示下的目标6D姿态估计 - [现已开源]
作者团队:德州大学 (UT-Austin)
论文:https://arxiv.org/abs/2001.01869
代码:https://github.com/chensong1995/HybridPose
LatentFusion: End-to-End Differentiable Reconstruction and Rendering for Unseen Object Pose Estimation
标题:将目标重构和渲染用于未知目标的端到端目标姿态估计网络 - [即将开源]
作者团队:华盛顿大学&英伟达 (NVIDIA)
论文:https://link.zhihu.com/?target=https%3A//arxiv.org/abs/1912.00416
代码:https://github.com/NVlabs/latentfusion
MoreFusion: Multi-object Reasoning for 6D Pose Estimation from Volumetric Fusion
标题:MoreFusion:基于体积融合的6D位姿估计的多目标推理 - [代码已开源]
作者团队:伦敦帝国学院 - 戴森(Dyson)机器人实验室
论文:https://arxiv.org/abs/2004.04336
代码:https://github.com/wkentaro/morefusion
EPOS:Estimating 6D Pose of Objects with Symmetries
标题:EPOS:使用对称性估计对象的6D姿态 - [即将开源]
作者团队: 捷克理工大学 & MTA SZTAKI
论文:https://arxiv.org/abs/2004.00605
主页:http://cmp.felk.cvut.cz/epos/
G2L-Net: Global to Local Network for Real-time 6D Pose Estimation with Embedding Vector Features
标题:全局到局部网络,利用嵌入向量特征进行实时6D姿态估计 - [现已开源]
作者团队:伯明翰大学 & 国防科技大学
论文:https://arxiv.org/abs/2003.11089
代码:https://github.com/DC1991/G2L_Net
PVN3D: A Deep Point-wise 3D Keypoints Voting Network for 6DoF Pose Estimation
标题:PVN3D: 基于 3D 关键点投票网络的 6DoF 姿态估计 - [现已开源]
作者团队:香港科技大学 & 旷视科技 & 快手
论文:https://arxiv.org/abs/1911.04231
代码:https://github.com/ethnhe/PVN3D
Single-Stage 6D Object Pose Estimation
标题:PVN3D: 基于 3D 关键点投票网络的 6DoF 姿态估计 - [现已开源]
作者团队:洛桑联邦理工学院 - CVLab
论文:https://arxiv.org/abs/1911.08324
代码:https://github.com/cvlab-epfl/single-stage-pose
相关链接:
3D视觉工坊 位姿估计
6D位姿估计开源