Equations in the paper
xianrui-luo opened this issue · comments
v_{proj} is just vector [0, 0, 1] and extract the last dimension (z axis) in the 3d point.
Thank you for replying.
CVPR 2021 "Camera Pose Matters: Improving Depth Prediction by Mitigating Pose Distribution Bias"
xianrui-luo opened this issue · comments
v_{proj} is just vector [0, 0, 1] and extract the last dimension (z axis) in the 3d point.
Thank you for replying.