AI-powered
podcast player
Listen to all your favourite podcasts with AI-powered features
Is There a Connection Between Computer Vision and Reconstruction?
The recognition is labeling those entities and then reconstruction is what filling in the gaps. So adding more information that's not there in the raw data. Yes. I started pushing this kind of a view in the around 2010 or something like that, because at that time in computer vision, people were just working on many different problems but treating them as separate isolated problem with its own data set. Now it turns out in the last five years or so in the post-deep learning revolution that this this architecture has turned out to be very conducive to that. There can be multiple output heads sharing common representations. In a certain sense, today, given the reality of what solutions people have to these. It is