Google patents 3D scene reconstruction from photos without camera data

1. A method performed by one or more computers, the method comprising: obtaining a plurality of images of a scene in an environment; and training, using the plurality of images, (i) an encoder neural network configured to receive an input image and generate, as output, a pose estimate that estimates a camera pose of a camera that captured the input image and (ii) a neural radiance field (NeRF) model that receives as input the pose estimate generated by the encoder neural network and generates a reconstruction of the input image, the training comprising: for each image in a set of one or more of the plurality of images: processing the image using the encoder neural network to generate a pose estimate for the image; applying an equivalence relation to the pose estimate to generate an equivalence class of a plurality of pose estimates; and for each of the plurality of pose estimates, processing the pose estimate using the NeRF model to generate a respective reconstruction of the image; and training the encoder neural network and the NeRF model on a loss function that measures, for each of the plurality of pose estimates for each of the one or more images, an error between the image and the respective reconstruction of the image generated from the pose estimate.