cameras.npz file about idr HOT 6 CLOSED

Hi, thank you for your work. Currently, I have these three files: cameras.bin/txt, cameras.bin/txt, poses3D.bin/txt. These 3 files contain all the data for my images. It seems from your previous reply that you are using individual.txt file for each image (/pos_{1}.txt'), can you provide me with any advice on how to obtain cameras.npz file? Thanks for you time~!

from idr.

+1. Any chance of how to obtain the .npz file? Been searching around everywhere for a solution for this.

from idr.

Hi,
Yes, the normalization code of the cameras is acting on cameras.npz file. For DTU, this npz file is a simple parsing of the txt files, meaning:

cameras = {}
n_cameras = 49 # or 64
scan_folder = 'DTU_preprocessed/scan65'
path_to_dtu_cameras = 'DTU/SampleSet/MVS Data/Calibration/cal18'
for i in range(n_cameras):
    filename = '{0}/pos_{1}.txt'.format(path_to_dtu_cameras, '%03d' % (i + 1))
    lines = open(filename).read().splitlines()
    lines = [[x[0], x[1], x[2], x[3]] for x in (x.split(" ") for x in lines)]
    P = np.asarray(lines).astype(np.float32).squeeze()
    P = np.concatenate([P, [[0, 0, 0, 1]]], 0)
    cameras['world_mat_%d' % i] = P
np.savez('{0}/cameras.npz'.format(scan_folder), **cameras)

And maybe you'll need to make this code compatible with your pathnames.

from idr.

Do we need to process the downloaded camera parameters in DTU dataset first before converting them to npz files?

from idr.

As can be seen in the code in the previous comment, the only thing that needs to do to the camera parameters is to make them 4x4 instead of 3x4.

from idr.

嗨，谢谢你的工作。目前，我有这三个文件：cameras.bin/txt、cameras.bin/txt、poses3D.bin/txt。这 3 个文件包含我的图像的所有数据。从您之前的回复看来，您对每张图片都使用了 individual.txt 文件（/pos_{1}.txt'），您能给我提供有关如何获取 camera.npz 文件的任何建议吗？谢谢你的时间~！

I have the same question , can you help me

from idr.