SSR-GS: Separating Specular Reflection in Gaussian Splatting for Glossy Surface Reconstruction

2026-03-05

AI Summary

This work addresses the challenge of accurately reconstructing glossy surfaces with strong specular reflections and complex interreflections under intricate lighting conditions, a task where existing 3D Gaussian splatting methods often fail. To this end, we propose SSR-GS, a novel framework that explicitly disentangles direct and indirect specular reflections within the Gaussian splatting paradigm for the first time. Direct reflections are modeled using a prefiltered Mip-Cubemap, while indirect reflections are captured via an IndiASG module. Furthermore, we introduce reflection-aware visual-geometric priors—including a reflection confidence score, progressive depth supervision, and normal constraints—to guide geometric optimization. Experiments demonstrate that our approach significantly improves both geometric accuracy and appearance fidelity on glossy surfaces across synthetic and real-world datasets, achieving state-of-the-art performance.

Technology Category

• Computer Vision: 3D Computer Vision
• Knowledge Representation and Reasoning: Geometric, Spatial, and Temporal Reasoning
• Search and Optimization: Mixed Discrete/Continuous Search

Application Category

• Search and Retrieval-Augmented AI: Personalized, context-aware and across-device search
• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

In recent years, 3D Gaussian splatting (3DGS) has achieved remarkable progress in novel view synthesis. However, accurately reconstructing glossy surfaces under complex illumination remains challenging, particularly in scenes with strong specular reflections and multi-surface interreflections. To address this issue, we propose SSR-GS, a specular reflection modeling framework for glossy surface reconstruction. Specifically, we introduce a prefiltered Mip-Cubemap to model direct specular reflections efficiently, and propose an IndiASG module to capture indirect specular reflections. Furthermore, we design Visual Geometry Priors (VGP) that couple a reflection-aware visual prior via a reflection score (RS) to downweight the photometric loss contribution of reflection-dominated regions, with geometry priors derived from VGGT, including progressively decayed depth supervision and transformed normal constraints. Extensive experiments on both synthetic and real-world datasets demonstrate that SSR-GS achieves state-of-the-art performance in glossy surface reconstruction.

Problem

• specular reflection
• glossy surface reconstruction
• 3D Gaussian splatting
• novel view synthesis
• interreflections

Innovation

• Gaussian Splatting
• Specular Reflection
• Glossy Surface Reconstruction
• Mip-Cubemap
• Visual Geometry Priors