Subhransu S. Bhattacharjee

Allows one to get the metric point cloud without using any further utilities and further allows the user to resize the resulting metric depth tensor to suite requirements.

Hi is there a way to build the inference pipeline using the DTU weights?

Why is there no direct way to work in known camera intrinsic and extrinsic in the reconstruction process?

13

I am fairly new to COLMAPs and I am using scale ambiguous data to perform COLMAP reconstruction with correct up to scale extrinsic and the known fx, fy, cx and...

Functional Approximation is poor

9

Congratulations on this great piece of work. I have tried to do simple tests like functional approximations and it turns out for a variety of models KANs are poor performing...

I had a great time reading the paper, but understanding the code was a bit difficult. I think its really important to make the basic unit as simple and clean...

KANvolver leads to 99.5% accuracy on MNIST dataset

5

Please check for reproduction and methods to further optimise: https://github.com/1ssb/torchkan

Same as title. As in extract from the data.npz in the folders as well as the .jpg.npy it seems like the downloads are often corrupted.

PLEASE ADD A LICENSE

1

PLEASE ADD A LICENSE

The scripts set of the igibson processing and traversability does not work because there are missing object categories also there are no safe list of urdfs (_best.urdf does not get...

CLI for Stable Diffusion Outpainting with the mask specified.