Giters

NVlabs / neuralangelo

Official implementation of "Neuralangelo: High-Fidelity Neural Surface Reconstruction" (CVPR 2023)

Home Page:https://research.nvidia.com/labs/dir/neuralangelo/

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Question about evaluation of PSNR.

HLinChen opened this issue · comments

commented

From your codes, I find you use all images for training on both tnt and dtu datasets. So what are the test images? Can you provide the indices of test images?

commented

Same, I gain a PSNR of 35.15 when validating on dtu_scan24 which surpasses the reported value 30.64 a large margin.

commented

Hi @HLinChen and @hbai98

We do not separate the training/test images when reporting PSNR. As mentioned in the paper, we use PSNR as a metric to assess the capacity to overfit the input images and capture details. I hope this helps!