densechen / cass Goto Github PK

Thanks for sharing your work.
I check that your results use the json file.
Can you share your result of ".pkl" types, like NOCS ??? (in the main paper, Figure 6).
It seems to be of great help when compared to other people with same formats.

Good afternoon, thank you for your work, I would very much like to conduct training, but today the link to the datasets does not work(
Maybe you saved the datasets on google drive or know some other workaround?
I also tried downloading as recommended in hughw19/NOCS_CVPR2019#59

Hello, I found that the evaluation is based on "gt_RTs_for_CASS" in predicted_result/gt/*_.json as the GT pose. Are gt_RTs GT poses from NOCS? Can you help me convert "gt_RTs" to "gt_RTs_for_CASS"?

你好，请问你的论文中 NOCS在32bins的设定下为什么会比原论文中的结果的大部分指标高一些？

你好，我运行了NOCS的检测程序会生成许多GT位姿可视化的图片（名为“*bbox_gt.png”）。从这些图片中明显可以看出一些物体的GT位姿不对，请问你的有没有遇到这样的情况？

Dear author, how does the batch mixing mentioned in the experiment be realized? Can you provide the relevant code?
Thanks very much!

作者你好！NOCS数据集提供的mask并没有将各个物体区分开，且没有提供目标物体的gt bbox。请问你们是怎么基于NOCS数据集对物体进行分割的？