Generating plausible hairstyles is a very challenging problem. Despite recent efforts no definite solution was presented so far. Many of the current limitations are related to the optical complexity of hair. In this paper we present a technique for hair reconstruction based on thermal imaging. By using this technique several issues of conventional image-based techniques, such as shadowing and anisotropy in reflectance, can be avoided. Moreover, hair-skin segmentation becomes a trivial problem, and no special care about lighting has to be taken, as the hair is "lit from inside" with the head as light source. The capture process is fast and requires a single hand-held device only. The potential of the proposed method is demonstrated by several challenging examples.

In this paper we present a novel efficient and fully automated technique to synthesize realistic facial hair-such as beards and eyebrows-on 3D head models. The method requires registered texture images of a target model on which hair needs to be generated. In a first stage of our two-step approach a statistical measure for hair density is computed for each pixel of the texture. In addition, other geometric features such as 2D pixel orientations are extracted, which are subsequently used to generate a 3D model of the individual hair strands. Missing or incomplete information is estimated based on statistical models derived from a database of texture images of over 70 individuals. Using the new approach, characteristics of the hair extracted from a given head may be also transferred to another target.

No abstract