cv-lab-x

请问下，结果图上这个点云和相机的显示是用什么工具显示的？

Hi, thanks for your great work! will wisp support that training ngp multi hash grid and joint sdf ?

batch_size and trainning time

1

hi, thanks for your great work! 1. why you use batch_size = 1 in your code, did your try to imcrease batch_size ? i got some errors when i just...

dist loss

3

hi, thanks for your great work! i test the distloss in real scene, but it doesn't work well about the floaters, my dist loss weight is 0.001. did your do...

samples in inverse depth or Euclidean space?

1

hi, thanks for your great work. I have some questions about samples in nerfacc, in mipnerf360, they do uniform samples in s-space(inverse depth), and transform sample pts from s-space to...

thanks for your work, the reconstruction results of the person Hall is wrong, what params should i adjust to get better results? i use the default params: `colmap feature_extractor \...

online SIBR viewer for 2dgs

3

hi, thanks for your great work, is there SIBR viewer for 2dgs, origin SIBR viewer for 3dgs not work for 2dgs Looking forward to your reply, thanks! @hbb1

hi, thanks for your greak work, how to inprove efficiency with more than 50 images ? @yocabon Looking forward to your reply, thanks.

train without dense/fused.ply

1

hi, thanks for your work, how to modify the codes to train without dense/fused.ply ? and train without 24 views @zehaozhu Looking forward to your reply, thanks

efficiency about the Fixed Culling

1

hi, thanks for your work, did you test the efficiency about the "Fixed Culling"? training time and rendering fps compare with origin diff-gaussian-rasterization ? Looking forward to your reply, thanks,...