Occupancy Network

This is the upgrade to Occupancy Grid.

An occupancy network is a continuous representation of the 3D space using a neural network to model the implicit surface of objects within the environment. It represents the occupancy as a continuous function over space.

But these are not really doing any object detection, simply Mapping.

Original paper: https://arxiv.org/abs/1812.03828

Resources

• A Look at Tesla’s Occupancy Networks
• https://www.youtube.com/watch?v=jPCV4GKX9Dw

Cool stuff

• https://pengsongyou.github.io/nice-slam
• https://pengsongyou.github.io/conv_onet

Why are occupancy networks?

Because classical object detection methods are limited… if the object is not in the dataset, the object is not detected. So there are always edge cases. Thus, we can instead train an occupancy network!!