GlossyGS: Inverse Rendering of Glossy Objects with 3D Gaussian Splatting

TL;DR

GlossyGS is a novel inverse rendering framework that accurately reconstructs geometry and materials of glossy objects by integrating material priors and a hybrid representation, improving over existing methods in fidelity and realism.

Contribution

The paper introduces GlossyGS, which uses micro-facet segmentation priors and a normal map prefiltering strategy within a hybrid geometry-material model for better glossy object reconstruction.

Findings

Effective high-fidelity geometry reconstruction.

Improved material decomposition for glossy surfaces.

Outperforms state-of-the-art methods in experiments.

Abstract

Reconstructing objects from posed images is a crucial and complex task in computer graphics and computer vision. While NeRF-based neural reconstruction methods have exhibited impressive reconstruction ability, they tend to be time-comsuming. Recent strategies have adopted 3D Gaussian Splatting (3D-GS) for inverse rendering, which have led to quick and effective outcomes. However, these techniques generally have difficulty in producing believable geometries and materials for glossy objects, a challenge that stems from the inherent ambiguities of inverse rendering. To address this, we introduce GlossyGS, an innovative 3D-GS-based inverse rendering framework that aims to precisely reconstruct the geometry and materials of glossy objects by integrating material priors. The key idea is the use of micro-facet geometry segmentation prior, which helps to reduce the intrinsic ambiguities and improve the decomposition of geometries and materials. Additionally, we introduce a normal map prefiltering strategy to more accurately simulate the normal distribution of reflective surfaces. These strategies are integrated into a hybrid geometry and material representation that employs both explicit and implicit methods to depict glossy objects. We demonstrate through quantitative analysis and qualitative visualization that the proposed method is effective to reconstruct high-fidelity geometries and materials of glossy objects, and performs favorably against state-of-the-arts.