原书出处
Foundations of Computer Vision (Antonio Torralba, Phillip Isola etc.)
This approach has many shortcomings. To start, we assumed that motion is discrete (it can only take on integer values). Therefore, the current approach does not compute displacements of pixels to subpixel accuracy that might be important if we need precision or if motions are very small. We could improve the approach by interpolating the cost function or by computing subpixel displacements using bilinear or
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/c046b.xhtml
EPUB SHA-256:60a7eebc43f5d9a675d776fed3736fbdaa791e55877023f2f8cba016a9b384f8