SSR-GS：在高光表面重建中分离镜面反射
SSR-GS: Separating Specular Reflection in Gaussian Splatting for Glossy Surface Reconstruction
AI总结：
SSR-GS通过引入预过滤Mip-Cubemap和IndiASG模块，结合视觉几何先验，有效分离镜面反射，提升高光表面重建性能。
摘要：
近年来，3D高斯散射（3DGS）在视图合成中取得了显著进展。然而，在复杂光照条件下准确重建高光表面仍具挑战性，尤其是在强镜面反射和多表面互反射的场景中。为了解决这一问题，我们提出了SSR-GS，一种用于高光表面重建的镜面反射建模框架。具体而言，我们引入了预过滤的Mip-Cubemap来高效建模直接镜面反射，并提出了IndiASG模块来捕捉间接镜面反射。此外，我们设计了视觉几何先验（VGP），通过反射分数（RS）将反射感知的视觉先验与之耦合，以降低反射主导区域的光度损失贡献，其中几何先验源自VGGT，包括逐步衰减的深度监督和变换的法线约束。在合成和真实世界数据集上的大量实验表明，SSR-GS在高光表面重建中实现了最先进的性能。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
