DSNeRF icon indicating copy to clipboard operation
DSNeRF copied to clipboard

Published 20 hours ago • verified publisher icon dunbar12138

Training on DTU

Open basit-7 opened this issue 1 year ago • 2 comments

Hi, I am a little confused about training and evaluating on DTU. You have mentioned in the paper that

We run COLMAP with the ground truth calibrated camera poses to get keypoints. Images are down-sampled to a resolution of 400 × 300 for training and evaluation.

1- Did you make any changes to the ground truth camera poses after you down-sampled images to 400 x 300? 2- imgs2poses.py does not create colmap_depth.npy. 3- Do you have a separate config file for DTU? 4- Where can I get cameras.npz from?

basit-7 avatar Jul 28 '22 09:07 basit-7

Thanks for your interest!

  1. Yes, we followed pixelnerf to preprocess the camera poses.
  2. What data are you using?
  3. We basically have the similar config as LLFF dataset. We'll add the config file soon.
  4. cameras.npz is in the DTU dataset. You can download the dataset here.

dunbar12138 avatar Aug 12 '22 02:08 dunbar12138

  1. colmap_depth.npy is not generated by imgs2poses.py, which is provided in training process.

czg-first avatar Feb 17 '23 09:02 czg-first