Dis-PU icon indicating copy to clipboard operation
Dis-PU copied to clipboard

Point Cloud Upsampling via Disentangled Refinement, CVPR, 2021

Results 11 Dis-PU issues
Sort by recently updated
recently updated
newest added

The model upsampling the coordinate information. Will RGB information be upsampled?

Hi Ruihui, It could be very helpful if you could share the x16 training dataset.

I got this error when I tried running the scripts in a docker image (https://hub.docker.com/r/nvidia/cuda/tags?page=1&name=ubuntu): with the same parameters mentioned in the readme file. tensorflow.python.framework.errors_impl.InternalError: 2 root error(s) found. (0)...

I have a question about the local refinement unit. In the essay, the author writed 'Next, to obtain the local point feature overFL, a common routine is to apply MLPs...

The paper says " ... to account for the relative importance among the K neighbors, we further regress a spatial weight W ... Then, we modify F_L via a convolution...

Dear authors, your paper is really great and the visualizations have good quality. Can you tell me which tool/software you use to render/display the point clouds in your paper. Thanks!...

There is this statement——from Common.Const import GPU,but Common.const not found

The paper says that you `expand the number of points in the feature space`, but from your implementation, if I got correct, the feature is concatenated with uniformly sampled 2d...

Hi, I'd like to know what GPUs you used and how long did it take to train on each dataset.

Hi, I got into trouble while I reproduced the results. ![Screenshot 2021-07-19 00:56:40](https://user-images.githubusercontent.com/32631453/126073985-94849f76-ce7e-4046-923c-e3e07285e202.png) Is there anyway that I can fix this problem?