原书出处
Foundations of Computer Vision (Antonio Torralba, Phillip Isola etc.)
The direct approach depicted in figure 49.1 learns to estimate optical flow directly from a pair of frames. This architecture makes no assumptions about which architectural priors are needed to compute optical flow from images. The architecture is trained end-to-end using ground truth optical flow.
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/c049.xhtml
EPUB SHA-256:60a7eebc43f5d9a675d776fed3736fbdaa791e55877023f2f8cba016a9b384f8