Abstract: Apparatuses, methods, systems, and program products are disclosed for surface animation during dynamic floor plan generation. An apparatus includes a display configured to receive touch input, a processor coupled to the display, and a memory that stores code executable by the processor. The code is executable by the processor to receive a user input associated with a surface of a structure presented on the display, generate, in response to the user input, a two-dimensional representation of the floor plan comprising a line segment representing the surface of the structure, determine at least one three-dimensional element associated with the line segment representing the surface on the two-dimensional representation of floor plan, and gradually highlight the surface shown on the display where the geometric plane that the line segment defines intersects with the at least one three-dimensional element associated with the line segment.

Abstract: During capture of a three dimensional mesh of an environment, a combination of user inputs and machine learning is used to place annotations within the three dimensional mesh environment interactively. When the full mesh is assembled, the annotations are used to detect which portions of the three-dimensional mesh make up the features of interest. Additional features can be derived from these results, such as a 2D image of a floor plan.

Abstract: Various embodiments described herein relate to a method, apparatus, and a non-transitory machine-readable storage medium including one or more of the following: locating a 2D plane correlated with a 3D mesh representing a surface of a room; taking a virtual 2D picture of a 3D mesh along the 2D segment; within the virtual 2D picture, finding a hole; determining the vertical picture floor, and hole width; when the hole intersects the vertical picture floor and is at least as wide as a door width then classifying the hole as a door; else classifying the hole as a window.

Abstract: A loop shape representing a floor plan is extracted from an imperfect or incomplete floor plan scan by applying building construction techniques to fill in missing information. The floor plan is shown to the user during all stages of assembly, allowing the user to make a purposeful mark on the display, changing how the incomplete scan is interpreted. Whenever a marking is placed the floor plan is regenerated.

Abstract: When given an incorrect polygonal representation of a floor plan, methods and systems described herein may be able to more accurately delineate the floorplan by optimizing between a function that determines how far in a solution vertices in the polygonal representation have moved and a function that determines how aligned the polygonal representation is.

Abstract: During capture of a three dimensional mesh of an environment, a combination of user inputs and machine learning is used to place annotations within the three dimensional mesh environment interactively. When the full mesh is assembled, the annotations are used to detect which portions of the three-dimensional mesh make up the features of interest. Additional features can be derived from these results, such as a 2D image of a floor plan.