Camera Localization

Learning Less is More – 6D Camera Localization via 3D Surface Regression:

MVSNet: Depth Inference for
Unstructured Multi-view Stereo:

Impressive. The source code will be published soon

Seems a little shaky without the training input 3D model, it would be interesting to see how it performs with training over a set of nadir video shots from a drone.

MVSNet paper also looks really interesting, but no source code. I doubt they’ll publish anything, as some of the authors are associated with altizure.

1 Like