| CPC G06T 19/006 (2013.01) [G06T 19/20 (2013.01); G06T 2219/2004 (2013.01)] | 20 Claims |
|
1. A method comprising:
determining floor plan data representing a top-down floor plan of a room;
determining a three dimensional (3D) room model comprising:
first window data representing a first size, a first position, and a first orientation of a first window in the 3D room model; and
first door data representing a second size, a second position, and a second orientation of a first door in the 3D room model;
receiving first intended usage data, the first intended usage data describing a usage intent for the room;
inputting first input data representing the floor plan data, the 3D room model, and the first intended usage data into a first machine learning model;
generating, by the first machine learning model, a first collection template comprising:
first bounding box data comprising a first plurality of 3D bounding boxes for the 3D room model, wherein a first 3D bounding box of the first plurality of 3D bounding boxes comprises:
first furniture category data identifying a first furniture category associated with the first 3D bounding box; and
first data comprising a third size, a third position, and a third orientation of the first 3D bounding box; and
generating a first populated collection template by selecting a respective first furniture item for each of the first plurality of 3D bounding boxes; and
rendering the first populated collection template on a display.
|