Head Reconstruction from Internet Photos
This addresses the need for full head modeling from casual photos, though it appears incremental by extending face-only methods to include the head.
The paper tackles the problem of 3D head reconstruction from uncalibrated Internet photos, which previous methods limited to just the face area, by proposing a method to reconstruct the rough shape of the entire head using a boundary-value growing algorithm, with results demonstrated on celebrity photos.
3D face reconstruction from Internet photos has recently produced exciting results. A person's face, e.g., Tom Hanks, can be modeled and animated in 3D from a completely uncalibrated photo collection. Most methods, however, focus solely on face area and mask out the rest of the head. This paper proposes that head modeling from the Internet is a problem we can solve. We target reconstruction of the rough shape of the head. Our method is to gradually "grow" the head mesh starting from the frontal face and extending to the rest of views using photometric stereo constraints. We call our method boundary-value growing algorithm. Results on photos of celebrities downloaded from the Internet are presented.