Provided is a method of generating a three-dimensional (3D) avatar from a two-dimensional (2D) image. The method may include obtaining a 2D image by capturing a face of a person, detecting a landmark of the face in the obtained 2D image, generating a first mesh model by modeling a 3D geometrical structure of the face based on the detected landmark, extracting face texture information from the obtained 2D image, determining a second mesh model to be blended with the first mesh model in response to a user input, wherein the first mesh model and the second mesh model have the same mesh topology, generating a 3D avatar by blending the first mesh model and the second mesh model, and applying, to the 3D avatar, a visual expression corresponding to the extracted face texture information.