Binbin Huang

Good suggestion! Currently there is not a viewer implemented. I will look into it.

This is a **great boost**!! Before moving grid_x and grid_y to GPU, the average training time on my RTX3090 GPU is about **50 min**.

Great work! But It seems like that the link is broken and I cannot access. I am highly appreciated if you would be able to PR or outline the changes....

Great. I found the correct link in your github profile. I will check it later.

Hi. it looks like you should increase the `depth_trunc`. the `depth_trunc` at least larger than the distance from the camera to the object. Or you just use unbounded mode `--unbounded`.

Hi, Thank you for your interest. I feel like I need help in implementing a CG viewer. As a CV guy, I may require some time to familiarize myself with...

Hi, you can refer to this script for processing the data. https://github.com/NVlabs/neuralangelo/blob/main/projects/neuralangelo/scripts/convert_tnt_to_json.py

Hi, since the DTU's intrinsic is not in ideal pinhole format; That is say, the principle point is not the image center. So I crop the image to be pinhole...

@leonwu0108 What do you mean the original size, the original 1600x1200 or the upscaled resolution? I don't think it will impact performance by using more pixels, although you may need...

I haven't tested ``cov3D_precomp`` , but it should work for that. But keep in mind that the `cov3D_precomp` should be a `3x3` homogeneous transformation matrix, ```python def setup(means3D, scales, quats,...