+1 for "serious cognitive dissonance"
Decades of research efforts being overshadowed by DL, it is hard to swallow for most researchers in CV community.
Decades of research efforts being overshadowed by DL, it is hard to swallow for most researchers in CV community.
DL doesn't provide solutions for challenges in robotics or augmented reality that CV is very good at. For example it can't place the camera at a specific position in the world using the image. DL can tell us what's in the image which CV can't. But CV can place the locations of those objects relative to the viewer.
I might be mistaken but isn't that exactly what this author's research was about? Camera pose estimation via Deep Learning ("PoseNet").