原书出处
Foundations of Computer Vision (Antonio Torralba, Phillip Isola etc.)
The reprojection loss (equation [39.51]) can be minimized by gradient descent, optimizing the three matrices, K, R, and T, directly. For the minimization to converge it is usually initialized with the solution obtained using DLT.
原书定位详情
来源:a19c7933-4eda-4176-aebd-30fe7e1ad292
正文位置:extracted/Foundations of Computer Vision (Antonio Torralba, Phillip Isola etc.)/_epub-src/OPS/xhtml/c039.xhtml
EPUB SHA-256:60a7eebc43f5d9a675d776fed3736fbdaa791e55877023f2f8cba016a9b384f8