Hannah Schieber

[FEATURE]: 3D bounding box ground truth genereration

1

Thanks for this awesome repository and nice work to easily generate syn. datasets. Its a really great contribution! **Is your feature request related to a problem? Please describe.** 3D object...

Error in test_ycb and test_lm

2

After downloading and installing I just run the demo and test files. I encounter the following error: ``` Traceback (most recent call last): File "train_lm.py", line 686, in train() File...

When training on ycbv we have the error that ist indices must be integers or slices not dict, this is weird as at the beginning for a few iterations it...

If the camera moves somewhere, where it already captured the surrounding but sth has changed (e.g. moved chair) will it update?

Question regarding the training

6

for how long was the model trained until the color of the lego changes?

Question regarding latent embedding

6

Is the latent embedding required? https://github.com/zubair-irshad/CenterSnap/blob/c2afd120428b0a07c88894da23311995b72bbbfd/prepare_data/generate_data_nocs.py#L202 how to obtain this from a new dataset? do i have to train NOCS?

quadratic images and depth of synthetic dataset

1

does nerf synthetic (own synthetic data) has to be quadratic? is there a specific reason for that check in the code?

Question regarding evaluation

4

So for eval a different dataset is used compared to training, how are the values for the dict obtained? eval: ``` (rgb=data['roi_img'].to(device), depth=data['roi_depth'].to(device), depth_normalize=data['depth_normalize'].to(device), obj_id=data['cat_id_0base'].to(device), camK=data['cam_K'].to(device), gt_mask=data['roi_mask'].to(device), gt_R=None, gt_t=None, gt_s=None,...

First of all great work, and nice repository. May you provide the config file for Linemod too?

Problem training on own blender dataset

2

Hey I created a custom dataset with blender from the original blender files, I face to following issue: ``` Iteration 04000: train_psnr = 17.97 test_psnr = 0.00 mse = 0.016522:...