Yang You: 3D Vision & Robotics
Collection
Papers, models, datasets and demos from Yang You (Stanford): object pose estimation, 3D keypoints and correspondence, CAD, robotics. β’ 31 items β’ Updated
Pretrained TensorFlow checkpoints for UKPGAN, a self-supervised 3D keypoint detector on rigid/non-rigid objects and real scenes, from:
UKPGAN: A General Self-Supervised Keypoint Detector (CVPR 2022)
Paper: arXiv:2011.11974 Β· Hugging Face paper page
Code and usage instructions: https://github.com/qq456cvb/UKPGAN
Project page: https://qq456cvb.github.io/projects/ukpgan
Checkpoints under outputs/<category>/tflogs/, matching the layout expected by the code:
airplane, chair, table β ShapeNet category models.smpl β non-rigid SMPL human models.universal β trained on a large collection of ShapeNet models (10+ categories), used for real-world scenes (3DMatch).Download into the root of the UKPGAN repo:
hf download qq456cvb/UKPGAN --local-dir .
python visualize.py --type shapenet --nms --nms_radius 0.1
@inproceedings{you2022ukpgan,
title={UKPGAN: A General Self-Supervised Keypoint Detector},
author={You, Yang and Liu, Wenhai and Ze, Yanjie and Li, Yong-Lu and Wang, Weiming and Lu, Cewu},
booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
year={2022}
}