NERF in the Wild Explained

Here I will tell you about "NERF in the wild" a research presented in August 2020 and which has all the features to revolutionize some application areas starting from ** Augmented and Virtual Reality **. The aim of the research is to produce a 3D visual synthesis of places starting from photographs of the same place very different from each other, taken at different times and with the automatic removal of objects / people that are not relevant to the object (done by the neural network itself during the process). Eg. the video of the Trevi fountain below was generated by NERF-W starting from public domain photographs on the Web and as you can see it was not only reproduced three-dimensionally but it is also possible to see it at different times of the day with different lights. Obviously all the tourists, cars, any advertising billboards, have been cleaned up. The intuition in this case is balanced between the use of a "standard" neural network, ie not a CNN or 3D-CNN (Convolutional Neural Networks -- born to be able to process photos / videos), and the basic rules of optics.