Closed drkoller closed 3 years ago
@drkoller could you please share your pair.txt files for the kicker and meadow sets? I cannot reproduce the results either.
Thanks!
@blablebli-robots, here are my pair.txt files:
kicker-pair.txt meadow-pair.txt
Do your F1 scores match mine closely?
@drkoller Thank you very much for sharing your files. My values are all over the place, I am getting just an unorganized point cloud in the final ply file. I tried from scratch with my own images and manually editing a pair.txt file, but again getting bad results.
Thanks for your feedback. The code is updated! I retest the code on high-res ETH3D training dataset and get almost the same results as those posted on the ETH3D website.
Thank you for making your code available!
I am trying to use your ACMP code to reproduce your reconstruction results that are posted on the ETH3D website and that were published in your AAAI-20 paper. My methodology is:
multi_view_training_dslr_undistorted.7z
) from the ETH3D websitecolmap2mvsnet_acm.py
with default parameters to convert the COLMAP files to MVSNet formatACMP
executable to reconstruct 3D point cloudsETH3DMultiViewEvaluation
to compute the F1 score at 2 cm toleranceWhen I use your code to reconstruct and evaluate the point clouds in this manner, I get some F1 scores that differ significantly from those posted on the ETH3D website:
(GitHub
code)
(ETH3D
website)
I realize that the algorithm is non-deterministic, and that F1 scores may vary slightly from one execution to the next. However, the F1 scores for the kicker and meadow datasets are much worse when I run this ACMP code, compared to the results posted on the ETH3D website.
What are the differences between the code posted in this repository and the code that was used to generate the results in the paper and posted on the ETH3D website?