image-matching-benchmark

image-matching-benchmark copied to clipboard

depth_clean = f['depth'].value gives errors and can be corrected like **depth_clean = f['depth'][:]** ______________________________________________________________ Then f2 = plt.imshow(data['depth'].astype(np.float)) can be corrected like **# f2 = plt.imshow(data['depth'])** ______________________________________________________________ changing plt.imshow(rgb.transpose((1, 2,...

mfatih7

I understand that it is an artificial thing, which likely would never happen in practice, but it is good to know anyway. https://github.com/ubc-vision/image-matching-benchmark/blob/master/utils/eval_helper.py#L99 Code to reproduce: ```python3 import numpy as...

ducha-aiki

[suggestion] leaderboard with limited number of keypoints

2

i think there should be a leaderboard with limited keypoints, such as 500 and 1000, which will be useful for selecting keypoint for realtime SLAM.

Vincentqyw

Accept subgroup-based matches.h5 files

2

To my best knowledge, you currently only accept `matches.h5` files with keys in form of `{filename1}-{filename2}`. I would request that support for `{filename1}/{filename2}` is added, which is interpreted by HDF...

jatentaki

Hello, Thanks for you work! I have a question about the error metrics: ``` # Compute err_q and err_t only when R, t are not None err_q, err_t = np.inf,...

alexs7

Image pairs feature point gt label tool

1

Hi, nice work! If Image pairs feature point gt label tool can share with us ?

DoongLi

colmap mapper fails on some bags (specially for bag size 5)

2

Hi, When I tried to evaluate on multiview, the bundle adjustment step couldn't converge and failed to generate colmap outputs. This happens for a few bags only. Around 5 bags...

rashikshrestha

how to evaluate on my own dataset?

1

I would like to evaluate various features on my own dataset, I read the parts of the theory of generating scene data, but I cannot find the script to do...

biggiantpigeon