Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
[IROS 2020] se(3)-TrackNet: Data-driven 6D Pose Tracking by Calibrating Image Residuals in Synthetic Domains
| Date | Stars |
|---|---|
| 2026-07-24 | 423 |
| 2026-07-25 | 423 |
| 2026-07-28 | 423 |
| 2026-07-30 | 423 |
| 2026-08-06 | 423 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
# iros20-6d-pose-tracking
This is the official implementation of our paper "se(3)-TrackNet: Data-driven 6D Pose Tracking by Calibrating Image Residuals in Synthetic Domains" accepted in International Conference on Intelligent Robots and Systems (IROS) 2020.
[[PDF]](https://arxiv.org/abs/2007.13866)
**Abstract:** Tracking the 6D pose of objects in video sequences is important for robot manipulation. This task, however, introduces multiple challenges: (i) robot manipulation involves significant occlusions; (ii) data and annotations are troublesome and difficult to collect for 6D poses, which complicates machine learning solutions, and (iii) incremental error drift often accumulates in long term tracking to necessitate re-initialization of the object's pose. This work proposes a data-driven optimization approach for long-term, 6D pose tracking. It aims to identify the optimal relative pose given the current RGB-D observation and a synthetic image conditioned on the previous best estimate and the object's model. The key contribution in this context is a novel neural network architecture, which appropriately disentangles the feature encoding to help reduce domain shift, and an effective 3D orientation representation via Lie Algebra. Consequently, even when the network is trained only with synthetic data can work effectively over real images. Comprehensive experiments over benchmarks - existing ones as well as a new dataset with significant occlusions related to object manipulation - show that the proposed approach achieves consistently robust estimates and outperforms alternatives, even though they have been trained with real images. The approach is also the most computationally efficient among the alternatives and achieves a tracking frequency of 90.9Hz.
**Applications:** model-based RL, manipulation, AR/VR, human-robot-interaction, automatic 6D pose labeling.
**This repo can be used when you have the CAD model of the target object. When such model is not available, checkout our another repo [BundleTrack](https://github.com/wenbowen123/BundleTrack), which can be instantly used for 6D pose tracking of novel unknown objects without needing CAD models**
# Bibtex
```bibtex
@article{wen2020se,
title={se(3)-TrackNet: Data-driven 6D Pose Tracking by Calibrating Image Residuals in Synthetic Domains},
url={http://dx.doi.org/10.1109/IROS45743.2020.9341314},
DOI={10.1109/iros45743.2020.9341314},
journal={2020 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)},
publisher={IEEE},
author={Wen, Bowen and Mitash, Chaitanya and Ren, Baozhang and Bekris, Kostas E.},
year={2020},
month={Oct} }
```
# (New) Application to visual feedback control
Some example experiments using se(3)-TrackNet in our recent work "Vision-driven Compliant Manipulation for Reliable, High-Precision Assembly Tasks", RSS 2021.
<img src="./media/ycb_packing.gif" width="600">
<img src="./media/cup_stacking_and_charger.gif" width="600">
<img src="./media/industrial_insertion.gif" width="600">
# Supplementary Video:
Click to watch
[<img src="./media/youtube_thumbnail.jpg" width="480">](https://www.youtube.com/watch?v=dhqM0hZmGR4)
# Results on YCB
<img src="./media/occlusion.gif" width="480">
<img src="./media/curves.jpg" width="480">
<img src="./media/ycb_results.jpg">
# About YCBInEOAT Dataset
<img src="./media/eoat1.jpg" width="1200">
<img src="./media/eoat2.jpg" width="1200">
Due to the lack of suitable dataset about RGBD-based 6D pose tracking in robotic manipulation, a novel dataset is developed in this work. It has these key attributes:
* Real manipulation tasks
* 3 kinds of end-effectors
* 5 YCB objects
* 9 videos for evaluation, 7449 RGBD in total
* Ground-truth poses annotated for each frame
* Forward-kinematics recorded
* Camera extrinsic parameters calibrated
Link to download this dataset is provided below under 'Data Preparation'.
Example manipulation sequence:
<img src="./mediaExcerpt of 8,981 characters
Read on GitHubWould you bet a product on this? Bounded 0–100 and slow moving.
matched fp:4b8a7e23247cc77e, topic:robotics, topic:manipulation, readme:manipulation
matched fp:4b8a7e23247cc77e, topic:synthetic-data, readme:synthetic data
matched fp:4b8a7e23247cc77e, topic:computer-vision, topic:pose-estimation
matched fp:4b8a7e23247cc77e, topic:dataset, readme:dataset