DIAMOND-SSS: Diffusion-Augmented Multi-View Optimization for Data-efficient SubSurface Scattering

TL;DR

DIAMOND-SSS is a novel framework that enables high-fidelity, relightable subsurface scattering reconstruction from extremely sparse data by leveraging diffusion models and geometric priors, significantly reducing data requirements.

Contribution

It introduces a diffusion-augmented, data-efficient method for subsurface scattering reconstruction that works with as few as ten images, outperforming previous approaches in data efficiency and quality.

Findings

Achieves state-of-the-art relightable Gaussian rendering quality.

Reduces real capture requirements by up to 90%.

Effectively reconstructs translucent materials from sparse data.

Abstract

Subsurface scattering (SSS) gives translucent materials -- such as wax, jade, marble, and skin -- their characteristic soft shadows, color bleeding, and diffuse glow. Modeling these effects in neural rendering remains challenging due to complex light transport and the need for densely captured multi-view, multi-light datasets (often more than 100 views and 112 OLATs). We present DIAMOND-SSS, a data-efficient framework for high-fidelity translucent reconstruction from extremely sparse supervision -- even as few as ten images. We fine-tune diffusion models for novel-view synthesis and relighting, conditioned on estimated geometry and trained on less than 7 percent of the dataset, producing photorealistic augmentations that can replace up to 95 percent of missing captures. To stabilize reconstruction under sparse or synthetic supervision, we introduce illumination-independent geometric priors: a multi-view silhouette consistency loss and a multi-view depth consistency loss. Across all sparsity regimes, DIAMOND-SSS achieves state-of-the-art quality in relightable Gaussian rendering, reducing real capture requirements by up to 90 percent compared to SSS-3DGS.