search

alejocb / dpptam

DPPTAM: Dense Piecewise Planar Tracking and Mapping from a Monocular Sequence
GNU General Public License v3.0
220 stars 82 forks source link

RANSAC is not updating inlier ratio & hypothesis? #10

Closed sunghoon031 closed 8 years ago

sunghoon031 commented 8 years ago

I am reading your paper and investigated the code a bit. I love your method and the amazing result it produces !! Here are some questions I have:

  1. Do you update the inlier ratio for RANSAC anywhere in the code? Because I found that ransac_for_3Dspx function is not really updating the inlier ratio & hypothesis, but rather using a fixed number (i.e. 99) of hypotheses.
  2. Correct me if I'm wrong: Is the published code "Semi-dense + 3DS (ours)" method? and is that the reason why the code doesn't involve the dense mapping part (section V.B in paper) ?

I will look forward to your reply. Thanks in advance !

Cheers, Seong.

alejocb commented 8 years ago

Hi,

Thank you for your interest in the code!

1-) It seems that I do not update it, I used to do it but I changed it at some point. I released the code 3 months after the conference and it is possible that some parts are changed, although the main ideas remain the same. I will upload an improved version of the code very soon, and there will be some changes that are not in the IROS paper.

2-) Yes.

Best regards, Alejo.

sunghoon031 commented 8 years ago

Thanks a lot !