An image processing apparatus designates a first partial region for a first image obtained by rendering a configuration of an object in accordance with a predetermined coordinate system, designates a second partial region corresponding to the first partial region for a second image including an image obtained by capturing the object, and converts an image of the second partial region into an image complying with the predetermined coordinate system based on a coordinate of the first partial region in the first image and a coordinate of the second partial region in the second image. In the designation of the first partial region, different first partial regions in the first image are sequentially designated, and a first partial region at a (k+1)-th time based on a first partial region designated at a k-th time.