question about the Occlusion LineMOD dataset

ethnhe / PVN3D

Code for "PVN3D: A Deep Point-wise 3D Keypoints Hough Voting Network for 6DoF Pose Estimation", CVPR 2020

MIT License

488 stars 105 forks source link

question about the Occlusion LineMOD dataset #63

Closed luzzou closed 3 years ago

luzzou commented 3 years ago

hello, thank you for your great work! I have a question about how to train the semantic segmentation branch on the Occlusion LineMOD dataset? Because it looks like this dataset has no ground truth semantic labels.

ethnhe commented 3 years ago

We trained the model on the LineMOD training set and only use the Occlusion LineMOD as the test set, following previous works.

luzzou commented 3 years ago

Got it, thanks!