A Biophysical 3D Morphable Model of Face Appearance

Decomposing Multispectral Face Images into Diffuse and Specular Shading and Biophysical Parameters

“…In principle, our model could be fitted to four channel data so it would be interesting to see whether we can obtain similar results using RGB + NIR images. Our inverse rendered results could be used to learn statistical models of the variation in intrinsic biophysical face parameters [16].…”

“…Our biophysical spectral reflectance model for skin follows a number of previous models [2,6,13,14], though we focus on simplicity and limiting the number of free parameters. Specifically, our model allows only the melanin and haemoglobin concentration to vary spatially whereas all other parameters are based on measured data, validated approximation functions or average values [2,13,[15][16][17][18][19][20]. The free parameters have physical meaning and can therefore be constrained to the range of values observed in healthy skin.…”

3D Morphable Face Models—Past, Present, and Future

“…Subsequently, this idea was extended to jointly model facial shape, texture, and attributes [Egger et al 2016b]. Alotaibi and Smith [2017] use the observation that skin color forms a nonlinear manifold in RGB space, approximately spanned by the colors of the pigments melanin and hemoglobin. They inverse render maps of these parameters and then construct a linear statistical model in the parameter space.…”

Real-Time Relighting of Human Faces with a Low-Cost Setup

“…If this happens close to the surface of the skin, we can approximate it as a diffuse reflectance, some times also referred to shallow scattering in the case of skin. However, human skin consists of several layers of biological tissue, which allow the light to traverse further into the skin and travel for a certain distance before being reemitted [2,19,39]. This effect is known as subsurface scattering and is de picted in Figure 2.1c.…”