The image processing apparatus of the present invention is an image processing apparatus that performs processing relating to a three-dimensional shape model generated by using a plurality of images obtained by a plurality of cameras capturing an object, and the image processing apparatus includes: a specification unit configured to specify, based on position information on an object at a first time, a processing area relating to a three-dimensional shape model of the object at a second time later than the first time; and a processing unit configured to perform processing relating to the three-dimensional shape model of the object at the second time for the processing area specified by the specification unit.