Reprojection Losses: Deep Learning Surpassing Classical Geometry in Computer Vision?

Once again thinking about geometry, Alex Kendall shares his thoughts about the role of reprojection losses for unsupervised learning in computer vision. He describes how such losses can be used to learn from stereo images and why this allows self-supervised learning. He then takes a deep look at some short-comings and how the approach may be improved upon.


Want to receive more content like this in your inbox?