Xianghui Yang

Hi, I also have some problems about the training. I tried to use downloaded pretrained models and my pretrained models to initialize the framework before joint training, but the results...

@pidan1231239 Hi, have you reproduced the results reported in the paper? I'm also trying to do it but only got 0.103016 (average chamfer distance).

Hi @mabaorui, I think your single-view reconstruction under chamfer distance L1 comparison is unfair. Results from Occupancy Networks are **scaled 10** but you forget the scale. Please check it here....

Hi @AlexsaseXie, have you found how to generate voxelized models? I'm also interested in it.

Hi @jchibane, I think @lykius is right here. The code here should be `samples = samples - F.normalize(gradient, dim=2) * df_pred.reshape(-1, 1)*2`. Because your inputs are grid coordinate points [-1,1]...

Hi, there. Thanks for your interest. For your first question, the parameters of the dataset.py are image and mask paths, the input size, and the mean and standard deviation of...

Thanks Liuyuan. I will have try. And I also have a question about the grid size. May I know the grid size used when calculating IoU?

Hi @liuyuan-pal, I notice you use the pose from external dependency. `from eval_utils import H, W, POSES, NUM_IMAGES, K` Could you provide an example about it?

Hi @liuyuan-pal, as you suggest, I have tried to replace the code by predefined poses in the pickle file. ``` H, W = 256, 256 NUM_IMAGES = 16 with open(f'meta_info/camera-16.pkl',...

Sorry for that. The function `get_10x_lr_params` should be `get_lr_params` and `Network `should be `Brinet`. I have corrected them.