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

TL;DR

This paper introduces GTSR, a novel pipeline using subsurface scattering-aware 3D Gaussians for efficient and accurate reconstruction of translucent object surfaces from multi-view images, outperforming existing methods.

Contribution

GTSR combines surface and interior Gaussians with Fresnel blending and Disney BSDF to effectively model and reconstruct translucent objects, addressing limitations of prior opaque-focused methods.

Findings

Outperforms baseline methods on NeuralTO Syn dataset

Achieves real-time rendering of translucent objects

Adapts to various translucent material properties

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.