GTSR: Subsurface Scattering Awared 3D Gaussians for Translucent Surface Reconstruction

2026-03-23

AI Summary

Surface reconstruction of translucent objects from multi-view images remains highly challenging due to their complex optical properties, which existing 3D Gaussian Splatting methods fail to model. This work proposes GTSR, the first approach to incorporate subsurface scattering awareness into the 3D Gaussian Splatting framework. It employs two distinct sets of Gaussians—one representing surface geometry and the other capturing subsurface scattering color—and fuses them through a Fresnel term during rendering. To enhance geometric fidelity, particularly in non-silhouette regions, the method integrates the Disney BSDF model and deferred rendering to impose stronger normal and depth constraints. Evaluated on the NeuralTO Syn dataset, GTSR outperforms current state-of-the-art techniques, supports real-time rendering, and generalizes effectively to diverse newly introduced translucent materials.

Technology Category

• Computer Vision: 3D Computer Vision
• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Knowledge Representation and Reasoning: Geometric, Spatial, and Temporal Reasoning

Application Category

• Security and Privacy: Data transparency and provenance
• Search and Retrieval-Augmented AI: Multilingual and cross-lingual Web search
• Systems and Infrastructure for Web, Mobile and WoT: Sustainability and carbon-aware systems for Web, mobile, and WoT

Abstract

Reconstructing translucent objects from multi-view images is a difficult problem. Previously, researchers have used differentiable path tracing and the neural implicit field, which require relatively large computational costs. Recently, many works have achieved good reconstruction results for opaque objects based on a 3DGS pipeline with much higher efficiency. However, such methods have difficulty dealing with translucent objects, because they do not consider the optical properties of translucent objects. In this paper, we propose a novel 3DGS-based pipeline (GTSR) to reconstruct the surface geometry of translucent objects. GTSR combines two sets of Gaussians, surface and interior Gaussians, which are used to model the surface and scattering color when lights pass translucent objects. To render the appearance of translucent objects, we introduce a method that uses the Fresnel term to blend two sets of Gaussians. Furthermore, to improve the reconstructed details of non-contour areas, we introduce the Disney BSDF model with deferred rendering to enhance constraints of the normal and depth. Experimental results demonstrate that our method outperforms baseline reconstruction methods on the NeuralTO Syn dataset while showing great real-time rendering performance. We also extend the dataset with new translucent objects of varying material properties and demonstrate our method can adapt to different translucent materials.

Problem

• translucent surface reconstruction
• subsurface scattering
• 3D Gaussian splatting
• multi-view reconstruction
• optical properties

Innovation

• 3D Gaussian Splatting
• Subsurface Scattering
• Translucent Object Reconstruction
• Fresnel Blending
• Disney BSDF