Towards the Probabilistic Fusion of Learned Priors into Standard Pipelines for 3D Reconstruction
Tristan Laidlow,Jan Czarnowski,Andrea Nicastro,Ronald Clark,Stefan Leutenegger,Tristan Laidlow,Jan Czarnowski,Andrea Nicastro,Ronald Clark,Stefan Leutenegger
The best way to combine the results of deep learning with standard 3D reconstruction pipelines remains an open problem. While systems that pass the output of traditional multi-view stereo approaches to a network for regularisation or refinement currently seem to get the best results, it may be preferable to treat deep neural networks as separate components whose results can be probabilistically fu...
