Spectral Subsurface Scattering from RGB via Biophysical Skin Inversion

2026-06-25

AI Summary

Existing subsurface scattering methods for skin rely on hand-tuned, homogeneous parameters, resulting in high authoring costs and physically inaccurate appearances. This work proposes an end-to-end approach that predicts full-spectrum scattering parameters from a single RGB diffuse albedo map. The key innovation lies in a hybrid medium representation that models multilayered skin as a combination of three uncorrelated scattering media. By integrating a chained neural decoder, a biophysical pigment mixing model, and random-walk path tracing, the method enables spectrally accurate subsurface scattering rendering grounded in real biophysical mechanisms. This framework substantially reduces manual intervention while significantly improving both the realism and computational efficiency of skin rendering.

Abstract

In this paper we present a spectral optical inversion for skin for path tracing-based rendering of subsurface scattering. Skin is a complex multilayered medium, with appearance determined by the mixture of biophysical chromophores. However, current methods rely on medium homogeneization, with optical parameters obtained via albedo inversion from a reflectance texture and hand-tuned scattering distance and anisotropy. This results into significant art-skilled manual labor for authoring, and an inaccurate scattering profile for skin. To solve these problems, we generalize existing albedo inversion techniques, and propose a framework that predicts full-spectral skin scattering parameters from a single RGB diffuse albedo. Our method builds upon a new mixture-of-media representation, that approximates the aggregated multilayered appearance of skin by mixing the aggregated scattering of three uncorrelated media. We train a chained neural decoder that maps RGB diffuse albedo to the optical properties of the mixture of media, including anisotropy, scattering radius and scattering albedo. Then, we show this mixture can be used in a random-walk-based path tracer with minimal modifications, by simply randomly selecting the medium to traverse.

Problem

• subsurface scattering
• skin rendering
• optical inversion
• biophysical chromophores
• albedo inversion

Innovation

• spectral subsurface scattering
• biophysical skin inversion
• mixture-of-media representation
• neural decoder
• path tracing