Method and system for combining images

A system of combining images, the system comprising at least one processor and a memory storing processor-executable codes, wherein the at least one processor is configured to implement the following operations upon executing the processor-executable codes:

• obtain a reference image including a first background and at least one first object;
• obtain a view intended for capturing in at least one further image, the view including a second background and at least one second object;
• automatically analyze the reference image to determine positions for the at least one second object from the view for combining into a combined image;
• present, on one or more Augmented Reality (AR) overlays on a screen, an AR guide to guide a user on merging the reference image and the at least one further image, the AR guide depicting, on the second background, a representation of the at least one first object and the at least one second object in the positions with respect to the at least one first object;
• obtain the at least one further image, the at least one further image being captured by the user upon selecting, by the user, the at least one second object in one of the positions depicted by the AR guide;
• automatically adjust lighting parameters of the at least one further image to match lighting parameters of the reference image;
• place the at least one second object on the at least one further image according to the one of the positions and storing the at least one further image with the at least one second object placed in the one of the positions;
• and
• seamlessly merge the reference image and the at least one further image into the combined image by placing the at least one second object into the reference image according to the one of the positions.

A non-transitory processor-readable medium having instructions stored thereon, which when executed by one or more computers, cause the one or more computers to implement a method of combining images, the method comprising:

• obtaining a reference image including a first background and at least one first object;
• obtaining a view intended for capturing in at least one further image, the view including a second background and at least one second object;
• automatically analyzing the reference image to determine positions for the at least one second object from the view for combining into a combined image;
• presenting, on one or more Augmented Reality (AR) overlays on a screen, an AR guide to guide a user on merging the reference image and the at least one further image, the AR guide depicting, on the second background, a representation of the at least one first object and the at least one second object in the positions with respect to the at least one first object;
• obtaining the at least one further image, the at least one further image being captured by the user upon selecting, by the user, the at least one second object in one of the positions depicted by the AR guide;
• automatically adjusting lighting parameters of the at least one further image to match lighting parameters of the reference image;
• placing the at least one second object on the at least one further image according to the one of the positions and storing the at least one further image with the at least one second object placed in the one of the positions;
• and
• seamlessly merging the reference image and the at least one further image into the combined image by placing the at least one second object into the reference image according to the one of the positions.