原书出处
Foundations of Computer Vision (Antonio Torralba, Phillip Isola etc.)
To deal with the ambiguities mentioned before, the model is trained to predict disparity (inverse depth up to scale and shift). This means that we can not directly use the output. We need to convert it first into world coordinates.
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/c055b.xhtml
EPUB SHA-256:60a7eebc43f5d9a675d776fed3736fbdaa791e55877023f2f8cba016a9b384f8