guwinston

Results 5 comments of guwinston

Bin size was too small in the coarse rasterization phase. This caused an overflow, meaning output may be incomplete.

I meet the same problem in my own data, is there any solution?

Training is too slow.

I am using an 4090 GPU and my training is also very slow. Is there a problem with the code?

Training is too slow.

@niujinshuchong I am using mipnerf360's bicycle scene, the image factor is 4，and I printed the number of Gaussian points in the training log. It seems that there are too many...

A question about the normal definition

I believe there may be an issue with the statement: **"The normal is always perpendicular to the intersection plane."** Consider the transformation of the world-space normal vector $n_i$ into local...

camera extri problem in cameras.json

> Met the same confusion. I think the variable name was wrong. `W2C = np.linalg.inv(Rt)` should be `C2W = ...`. Yes, I think so, too. This may be a writing...