TODO

1. 待测试的网络

Yolo-6D (寻芝任)

paper: Real-Times Seamless Single Shot 6D Object Pose Prediction

code: https://github.com/Mmmofan/YOLO_6D

DenseFusion (徐隆)

paper: DenseFusion: 6D Object Pose Estimation by Iterative Dense Fusion

code: https://github.com/MyoungHaSong/DenseFusion_ROS

6-PACK

paper: 6-PACK: Category-level 6D Pose Tracker with Anchor-Based Keypoints

code: https://github.com/j96w/6-PACK

Deep Object Pose Estimation （樊家乐）

paper: Deep Object Pose Estimation for Semantic Robotic Grasping of Household Objects

code: https://github.com/NVlabs/Deep_Object_Pose

PVN3D （方莹）

paper: PVN3D: A Deep Point-wise 3D Keypoints Voting Network for 6DoF Pose Estimation

code: https://github.com/ethnhe/PVN3D

2. 网络推断加速工具

• TensorRT
• nimble: https://github.com/snuspl/nimble

3. 数据集录制+标注

4. 模型训练+调试

资料汇总

• https://paperswithcode.com/task/6d-pose-estimation-1/latest

• 17篇6D姿态估计算法汇总（含论文，代码及解读）

• 6D姿态估计算法汇总

• [综述] Vision-based Robotic Grasping: Papers and Codes

  • Chinese version: 刚体6D位姿估计方法综述