iros20-6d-pose-tracking
Pose estimator
An optimization approach for long-term 6D pose tracking of objects in video sequences using synthetic data and a novel neural network architecture.
[IROS 2020] se(3)-TrackNet: Data-driven 6D Pose Tracking by Calibrating Image Residuals in Synthetic Domains
391 stars
16 watching
68 forks
Language: Python
last commit: about 3 years agoLinked from 2 awesome lists
3d6d-pose-estimation6dof-pose6dof-trackingcomputer-visiondatasetdomain-adaptationhuman-robot-interactionmanipulationpose-estimationrobotroboticsrobotssynthetic-datasynthetic-domainstrackingycbycb-video
Related projects:
| Repository | Description | Stars |
|---|---|---|
| A system for tracking the 6D pose of novel objects without requiring any prior knowledge of their 3D models or instance identities. | 623 | |
| A PyTorch implementation of a deep learning model for 3D multi-person pose estimation from a single RGB image | 825 | |
| Real-time pose estimation for mobile devices using deep neural networks and optimized models. | 1,003 | |
| A deep learning framework for multi-view fusion network-based 3D human motion capture system | 52 | |
| A MATLAB project that uses deep learning and stereo cameras to estimate 3D human pose from image data | 43 | |
| An implementation of a real-time 3D multi-object tracking system using off-the-shelf detectors and Kalman filters. | 1,690 | |
| A system for real-time and accurate full-body multi-person pose estimation and tracking using deep learning models. | 21 | |
| Provides software to estimate head pose from images and videos using deep learning techniques. | 1,588 | |
| Estimates object poses and positions in 3D space from RGB images | 1,031 | |
| Implementation of a 6D object pose estimation method using hybrid representations | 422 | |
| A PyTorch toolkit for 2D human pose estimation with support for multi-thread data loading, multi-GPU training, and visualization. | 1,109 | |
| An implementation of human instance segmentation based on pose estimation | 529 | |
| A framework for unsupervised depth and ego-motion estimation from monocular videos using deep learning | 1,977 | |
| Training and experimentation code for human pose estimation using stacked hourglass networks. | 575 | |
| Enables a robot to maintain scene descriptions at the object level by segmenting and tracking objects in real-time from RGB-D images. | 502 |