Accurate Full Body Scanning from a Single Fixed 3D Camera

3D body modeling has been a long studied topic in computer vision and computer graphics. While several solutions have been proposed using either multiple sensors or a moving sensor, we propose here an approach when the user turns, in a natural motion, in front of a fixed 3D low cost camera. This opens the door to a wide range of applications where scanning is performed at home. Our scanning system can be easily set up and the instructions are straightforward to follow. We propose an articulated, part-based cylindrical representation for the body model, and show that accurate 3D shape can be automatically estimated from 4 key views detected from a depth video sequence. The registration between 4 key views is performed in a top-bottom-top manner which fully considers the kinematic constraints. We validate our approach on a large number of users, and compare accuracy to that of a reference laser scan. We show that even using a simplified model (5 cylinders) an average error of 5mm can be consistently achieved.