Lightweight method estimates skin scattering for real-time rendering
A Lightweight Differentiable Method for Real-Time Skin Rendering and Digitization
Computer Vision and Pattern RecognitionGraphics
Summary
Creating realistic skin in video games and interactive apps usually needs slow, complex calculations. The authors developed a simpler method that uses just one light and one camera angle to figure out how light scatters under the skin. Their approach works fast enough for live applications and produces skin looks that match what real skin would do. They tested it on many people with diverse skin tones and also checked it with computer-generated images to make sure it works well.
What this means in practice
- •For game developers: Create realistic skin appearances in games using a fast method compatible with standard real-time shaders.
- •For digital character artists: Capture and optimize skin textures and scattering properties with minimal equipment for use in animation and virtual production.
Authors
Mario Marquez-Balduque, Carlos Rodriguez-Pardo, Jorge Lopez-Moreno
Abstract
Inverse rendering for skin typically relies on offline path tracing to estimate physical properties, which fail to map directly to the approximate shaders utilized in interactive applications, such as game engines. We bridge this gap by directly estimating subsurface scattering parameters tailored for real-time rendering pipelines. We introduce a differentiable Screen-Space Subsurface Scattering (SSSS) framework that enables the joint optimization of spatially varying base textures and scattering distances. To account for local variations in skin thickness, we estimate these parameters across distinct facial regions, generating a blended profile map ready for production runtime engines. Our pipeline utilizes a low-cost, single-light, single-view capture setup designed for accessible and practical appearance acquisition. Optimization is driven by a masked loss function targeting regions where subsurface scattering effects are dominant. We validate our approach on a real-world dataset of $45$ individuals across the Monk Skin Tone Scale, ensuring demographic generalization. Furthermore, we complement this evaluation with synthetic data, a multi-light setup validating our single-light assumption, and a tilted-view configuration confirming angular consistency. Results demonstrate that our method effectively recovers scattering parameters from lightweight inputs, yielding realistic skin appearance directly compatible with standard real-time shaders.