2d_to_3d | shot approach

2d_to_3d is a Jupyter Notebook library. 2d_to_3d has no bugs, it has no vulnerabilities and it has low support. However 2d_to_3d has a Non-SPDX License. You can download it from GitHub.

We propose a single-shot approach for simultaneously detecting an object in an RGB image and predicting its 6D pose without requiring multiple stages or having to examine multiple hypotheses. The key component of our method is a new CNN architecture inspired by the YOLO network design that directly predicts the 2D image locations of the projected vertices of the object's 3D bounding box. The object's 6D pose is then estimated using a PnP algorithm. Paper, arXiv. If you use this code, please cite the following. @inproceedings{tekin18,       TITLE = {{Real-Time Seamless Single Shot 6D Object Pose Prediction}},       AUTHOR = {Tekin, Bugra and Sinha, Sudipta N. and Fua, Pascal},       BOOKTITLE = {CVPR},       YEAR = {2018} }.