Pre-processing method for creating 3D virtual model and computing device therefor

A computing device comprising a memory for storing one or more instructions and at least one processor for executing the one or more instructions stored in the memory, wherein the one or more instructions cause, when executed by the at least one processor, the at least one processor to:

• prepare a plurality of data sets, each of which is created from a plurality of photographing points in an indoor space and includes image data;
• determine whether an object to be deleted exists in the image data;
• if the object to be deleted exists in the image data, delete data in an area corresponding to the object to be deleted from the image data;
• and
• fill a hole area created by deleting the data in the area corresponding to the object to be deleted using a neural network,
• wherein the image data is panoramic image data including 360-degree image for any one of the plurality of photographing points,
• wherein in determining whether an object to be deleted exists in the image data, the processor is configured to:
• detect at least one object existing in the image data using a first neural network that identifies an object;
• and
• identify whether the at least one object is the object to be deleted, and
• wherein in detecting at least one object existing in the image data using the first neural network, the processor is configured to:
• create at least one planar transformed image data by planar transforming a panoramic image data;
• and
• detect at least one object existing in the at least one planar transformed image data using the first neural network learned based on the at least one planar transformed image data.

A non-transitory storage medium for storing computer-readable instructions, wherein the instructions, when executed by a computing device, cause the computing device to perform the operations of:

• determining whether an object to be deleted exists in the image data;
• if the object to be deleted exists in the image data, deleting data in an area corresponding to the object to be deleted from the image data;
• and
• filling a hole area created by deleting the data in the area corresponding to the object to be deleted using a neural network,
• wherein the image data is panoramic image data including 360-degree image for any one of the plurality of photographing points,
• wherein the determining whether an object to be deleted exists in the image data comprises:
• detecting at least one object existing in the image data using a first neural network that identifies an object;
• and
• identifying whether the at least one object is the object to be deleted, and
• wherein the detecting at least one object existing in the image data using the first neural network comprises:
• creating at least one planar transformed image data by planar transforming a panoramic image data;
• and
• detecting at least one object existing in the at least one planar transformed image data using the first neural network learned based on the at least one planar transformed image data.