原书出处
Foundations of Computer Vision (Antonio Torralba, Phillip Isola etc.)
The network can also take as input multiple frames and not just two. 49.3 Concluding Remarks Supervised and unsupervised learning-based methods are now the state-of-the-art in motion estimation. But an accurate solution is still missing. One important question is, do we really need learning in order to solve this problem? Should we abandon the derivation of physically motivated algorithms for motion estimation that require no
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