Abstract: A method that includes obtaining images of an environment that are captured by one or more image capture devices, determining intrinsic parameters and extrinsic parameters of the one or more image capture devices that are associated with each of the images, creating a differentiable radiance field associated with the environment, and generating a three-dimensional representation of the environment. The three-dimensional representation contains one or more portions of the environment uncaptured in the images.

Abstract: The disclosure generally pertains to generating floorplans. An example method to do so involves generating a three-dimensional polygonal mesh representation of at least a portion of a building (one floor of the building, for example). The three-dimensional polygonal mesh representation is generated from images captured by a smartphone, for example. The method further includes generating an edge existence probability mask based on depth information obtained by using a LiDAR device on the smartphone, for example. The edge existence probability mask represents a confidence level associated with identifying an edge of a wall. A pictorial rendering of the building or a part of the building can be generated based on identifying edges and walls of the building by utilizing the three-dimensional polygonal mesh representation and the edge existence probability mask. The pictorial rendering may be used, for example, to provide interior design assistance with respect to a room of the building.