Giters

Brummi / MonoRec

Official implementation of the paper: MonoRec: Semi-Supervised Dense Reconstruction in Dynamic Environments from a Single Moving Camera (CVPR 2021)

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

How to run on my own data

JustC0deIt opened this issue · comments

commented

Hi.First of all, thank you for your efforts, and I am also surprised by the effect.
If I want to make predictions in my own data, how should I get the configs

commented

Hi,
thank you for your interest!
What kind of data do you have available?
For inference, you require 1. images (or video from which you can extract frames) 2. camera calibration (projection matrix) and 3. camera poses.
Some of this can be obtained from SLAM systems like DSO or ORB-SLAM.

Best,
Felix

commented

thanks for your time,now i have sequential pictures(RGB) extracted from video,and can i get the camera poses from DVSO or other algorithm？I used to get them by SuperPoint / SuperGlue inaccurately