Non-Linear Least Squares Minimization, with flexible Parameter settings, based on scipy.optimize, and with many additional classes and methods for curve fitting.
这套源码里我建议用 SIFT 而不是 ORB。 原因很直接：SIFT 在尺度变化和大角度视角变化下匹配质量明显更好，单目拍摄时相机位置不同，特征点的尺度和视角差异比双目更大。 代价是速度慢一点，但对离线重建来说完全能接受。 python import cv2 import numpy as np ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results