Differentiable SSSS framework brings single-image real-time skin digitization to game engines
ssh4net · x · 2026-11-12
A new paper by Mario Marquez-Balduque, Carlos Rodriguez-Pardo and Jorge Lopez-Moreno introduces a differentiable Screen-Space Subsurface Scattering (SSSS) framework that bridges inverse skin rendering and real-time pipelines.
- Jointly optimizes spatially-varying base textures and scattering distances, avoiding offline path tracing whose outputs don't map to approximate game-engine shaders
- Estimates parameters per facial region (ear, cheek, forehead, neck, nose) to capture local skin-thickness variation, producing blended profile maps ready for production runtime engines
- Acquisition uses a projector-camera strip-light setup with ambient baseline, structured/inverted stripes, and flat-field patterns; scattering is estimated from single-image captures
- Results span the Monk skin tone scale with close capture-vs-render stripe agreement
More from Research
- E11 Bio hiring computational scientist for petabyte imaging and agentic AI labs — anderssandberg · 2026-11-12
- EPFL: Claude writes EEG network weights by reasoning, matching gradient training with 6x fewer subjects — epfl-ch · 2026-11-12
- NeurIPS paper proves when RNN+MLP can provably recover true robot state — chriswolfvision · 2026-11-12
- Curated 9-paper reading list for LLM quantization beginners, from QLoRA to BitNet — East-Muffin-6472 · 2026-11-12
- A Quick Diagnostic Guide to 4 Common ML Training Errors and Their Causes — cneuralnetwork · 2026-11-12
- Anthropic's Lance Martin Scaled 1,000 Claude Agents to Formalize Fermat's Last Theorem — FinanceYF5 · 2026-11-12