Taeyeop Lee

I solved the problem using some tricks. If you can share some comments related to your experiences, It would be really helpful. https://github.com/ethnhe/FFB6D/blob/3579a69df27451f74f3abc06964bba1bc7d40605/ffb6d/train_lm.py#L109 I changed CUDA_VISIBLE_DEVICES and others ``` os.environ['CUDA_VISIBLE_DEVICES']...

As I understood, usually LM_O used the same weights as LM, because it doesn't have training data for LM_O. @ethnhe Does it right?? @Mr2er0 Have you evaluated the LM_O?? I...

@a7az0th @klueska I have the same problem. Currently, I have no files of `/usr/lib/x86_64-linux-gnu/libnvoptix.so.1`. Any tips would be welcome. Q1. I wonder that can I download `libnvoptix.so.1` only without reinstalling...

Thanks for the quick reply. I also tried the official NVIDIA Optix download from this website. (https://developer.nvidia.com/designworks/optix/download) After installing it, the `/usr/lib/x86_64-linux-gnu/libnvoptix.so.1` file was not appeared. I'm not sure this...

@pculbertson Did you solve your problem for `real_test`?? I also can't find the camera pose labels for `real_train`. Can you share the `real_train` and `real_test` pose.txt files with me ([email protected])??...

Thanks, I will recheck it!

Thanks for the explanation! I understood each component but still have some misunderstandings. Sorry for my poor understanding. **Q1. Can you explain each experimental setting clearly??** It would be really...

I think it is not desirable to compare z for all model(single class, car) shapes and one model shape with one DSDF as an ablation study. Because [the original DeepSDF...

@fylwen Do you get the textured mesh?

(1) As you know, the CAMERA25 dataset comes from the ShapeNet, as mentioned in the original NOCS paper, > we introduce a spatially context-aware mixed reality method to automatically generate...