Creating Neural Search and Rescue Fly-Through Environments with Mega-NeRF

A new research collaboration between Carnegie Mellon and autonomous driving technology company Argo AI has developed an economical method for generating dynamic fly-through environments based on Neural Radiance Fields (NeRF), using footage captured by drones. Mega-NeRF offers interactive fly-bys based on drone footage, with on-demand LOD. For more detail (at better resolution), check out the video embedded at the end of this article. The new approach, called Mega-NeRF, obtains a 40x speed-up compared to the average Neural Radiance Fields rendering standard, as well as offering something notably different from the standard tanks and temples that recur in new NeRF papers. The new paper is titled Mega-NeRF: Scalable Construction of Large-Scale NeRFs for Virtual Fly-Throughs, and comes from three researchers at Carnegie Mellon, one of whom also represents Argo AI.