# Decomposing multispectral face images into diffuse and specular shading and biophysical parameters

## TL;DR

This paper introduces a new spectral skin reflectance model that accurately decomposes multispectral face images into diffuse and specular components and estimates biophysical parameters like melanin and haemoglobin from a single image.

## Contribution

It presents a novel biophysical and dichromatic reflectance model and a fitting method that works from a single image without complex setups, enabling high-quality skin analysis.

## Key findings

- Accurate estimation of diffuse and specular shading
- Quantitative biophysical parameter maps (melanin, haemoglobin)
- Effective decomposition and editing of skin images

## Abstract

We propose a novel biophysical and dichromatic reflectance model that efficiently characterises spectral skin reflectance. We show how to fit the model to multispectral face images enabling high quality estimation of diffuse and specular shading as well as biophysical parameter maps (melanin and haemoglobin). Our method works from a single image without requiring complex controlled lighting setups yet provides quantitatively accurate reconstructions and qualitatively convincing decomposition and editing.