Abstract: One or more neural networks generate a first vector field from an input image and a reference image. The first vector field is applied to the input image to generate a first warped image. The training of the neural networks is evaluated via one or more objective functions. The neural networks are updated in response to the evaluating. The neural networks generate a second vector field from the input image and the reference image. A number of degrees of freedom in the first vector field is less than a number of degrees of freedom in the second vector field. The second vector field is applied to the input image to generate a second warped image. The neural networks are evaluated via the one or more objective functions, the reference image and the second warped image. The networks are updated in response to the evaluating.

Abstract: One or more neural networks generate a first vector field from an input image and a reference image. The first vector field is applied to the input image to generate a first warped image. The training of the neural networks is evaluated via one or more objective functions. The neural networks are updated in response to the evaluating. The neural networks generate a second vector field from the input image and the reference image. A number of degrees of freedom in the first vector field is less than a number of degrees of freedom in the second vector field. The second vector field is applied to the input image to generate a second warped image. The neural networks are evaluated via the one or more objective functions, the reference image and the second warped image. The networks are updated in response to the evaluating.

Abstract: A technique for generating a three-dimensional reconstruction of a scene involves generating a high-fidelity point cloud representing a three-dimensional reconstruction of a scene from two-dimensional images generated by at least one sensor whose position and orientation are known relative to a fixed coordinate system for each of the images. The high-fidelity point cloud is generated in a relative coordinate system without regard to the position and orientation of the sensor(s). A low-fidelity point cloud is generated in the fixed coordinate system from the two-dimensional images using the position and orientation of the sensor(s) relative to the fixed coordinate system.