I researched the monocular 3D object frameworks, especially the keypoint-based functions: CornerNet and CenterNet.
The CenterNet 3D object detection used the CornerNet keypoint detection backborn(Hourglass network), which shows a great performance on keypoint detection. I want to make some improvements on the orientation detection, which used 8 variables in CenterNet. … Continue Reading ››
2.I signed up for a 3D vision course online, and this week I learned the overview of 3D vision.And calculation of monocular and binocular point cloud depth map(The homework is SAD binocular matching algorithm).