https://github.com/cuge1995/u6da
official Pytorch implementation of paper 'Adversarial samples for deep monocular 6D object pose estimation'
https://github.com/cuge1995/u6da
6d 6dof-pose adversarial-attacks adversarial-defense adversarial-examples adversarial-machine-learning pose-estimation
Last synced: 3 months ago
JSON representation
official Pytorch implementation of paper 'Adversarial samples for deep monocular 6D object pose estimation'
- Host: GitHub
- URL: https://github.com/cuge1995/u6da
- Owner: cuge1995
- License: mit
- Created: 2022-03-01T03:43:17.000Z (over 3 years ago)
- Default Branch: main
- Last Pushed: 2022-05-29T01:48:55.000Z (about 3 years ago)
- Last Synced: 2025-01-12T22:33:00.498Z (5 months ago)
- Topics: 6d, 6dof-pose, adversarial-attacks, adversarial-defense, adversarial-examples, adversarial-machine-learning, pose-estimation
- Homepage: https://arxiv.org/abs/2203.00302
- Size: 4.88 KB
- Stars: 8
- Watchers: 2
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# U6DA
official Pytorch implementation of paper '[Adversarial samples for deep monocular 6D object pose estimation](https://arxiv.org/abs/2203.00302)'## U6DA-Linemod
The dataset can be download from [Google Drive](https://drive.google.com/file/d/1jmELumR2CuIXv1urLykoHoFtiMdg9xWx/view?usp=sharing) and [Baidu Pan](https://pan.baidu.com/s/12VREdD1BqFRTUtE-laomJg) (code: jcfm)After download and unzip, back up the original data first, then:
```
cp ape/* lm/test/000001/rgb/
cp benchvise/* lm/test/000002/rgb/
cp cam/* lm/test/000004/rgb/
cp can/* lm/test/000005/rgb/
cp cat/* lm/test/000006/rgb/
cp driller/* lm/test/000008/rgb/
cp duck/* lm/test/000009/rgb/
cp eggbox/* lm/test/000010/rgb/
cp glue/* lm/test/000011/rgb/
cp holepuncher/* lm/test/000012/rgb/
cp iron/* lm/test/000013/rgb/
cp lamp/* lm/test/000014/rgb/
cp phone/* lm/test/000015/rgb/
```* Our codes coming soon!
## Citation
if you find our work useful in your research, please consider citing:
```
@article{zhang2022adversarial,
title={Adversarial samples for deep monocular 6D object pose estimation},
author={Zhang, Jinlai and Li, Weiming and Liang, Shuang and Wang, Hao and Zhu, Jihong},
journal={arXiv preprint arXiv:2203.00302},
year={2022}
}
```