原书出处
Foundations of Computer Vision (Antonio Torralba, Phillip Isola etc.)
To find the final set of 3D points, the camera poses and the 3D locations of the keypoints are then further refined by bundle adjustment (camera intrinsics are refined too, if needed). The reprojection error loss is usually rewritten using a robust cost function (typically the Huber kernel).
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/c044.xhtml
EPUB SHA-256:60a7eebc43f5d9a675d776fed3736fbdaa791e55877023f2f8cba016a9b384f8