反射解锁：三维高斯泼溅中几何感知的反射解耦用于逼真场景渲染
Reflections Unlock: Geometry-Aware Reflection Disentanglement in 3D Gaussian Splatting for Photorealistic Scenes Rendering
AI总结：
针对现有方法将反射误认为几何导致重建质量差的问题，提出基于3DGS的Ref-Unlock框架，通过双分支与高阶球谐函数解耦反射，结合伪深度图和几何约束，提升真实场景渲染质量与编辑能力。
摘要：
在新型视图合成中，准确渲染具有反射表面的场景仍然是一个重大挑战，因为现有方法如神经辐射场（NeRF）和三维高斯泼溅（3DGS）常常将反射误认为是物理几何，导致重建质量下降。先前的方法依赖于不完整且不可泛化的几何约束，导致高斯溅射的位置与实际场景几何之间出现错位。当处理包含复杂几何的真实世界场景时，高斯的累积进一步加剧了表面伪影并导致重建模糊。为了解决这些局限性，在本工作中，我们提出了Ref-Unlock，一种基于三维高斯泼溅的新型几何感知反射建模框架，该框架明确解耦透射和反射分量，以更好地捕捉复杂反射并增强真实世界场景中的几何一致性。我们的方法采用双分支表示与高阶球谐函数来捕捉高频反射细节，同时配备反射去除模块，提供伪无反射监督以引导干净的分解。此外，我们整合了伪深度图和几何感知的双边平滑约束，以增强分解中的三维几何一致性和稳定性。大量实验表明，Ref-Unlock显著优于经典的基于GS的反射方法，并与基于NeRF的模型取得了竞争性结果，同时支持灵活的视觉基础模型（VFM）驱动的反射编辑。因此，我们的方法为反射场景的逼真渲染提供了一种高效且可泛化的解决方案。我们的代码可在https://ref-unlock.github.io/获取。
英文摘要：
Accurately rendering scenes with reflective surfaces remains a significant challenge in novel view synthesis, as existing methods like Neural Radiance Fields (NeRF) and 3D Gaussian Splatting (3DGS) often misinterpret reflections as physical geometry, resulting in degraded reconstructions. Previous methods rely on incomplete and non-generalizable geometric constraints, leading to misalignment between the positions of Gaussian splats and the actual scene geometry. When dealing with real-world scenes containing complex geometry, the accumulation of Gaussians further exacerbates surface artifacts and results in blurred reconstructions. To address these limitations, in this work, we propose Ref-Unlock, a novel geometry-aware reflection modeling framework based on 3D Gaussian Splatting, which explicitly disentangles transmitted and reflected components to better capture complex reflections and enhance geometric consistency in real-world scenes. Our approach employs a dual-branch representation with high-order spherical harmonics to capture high-frequency reflective details, alongside a reflection removal module providing pseudo reflection-free supervision to guide clean decomposition. Additionally, we incorporate pseudo-depth maps and a geometry-aware bilateral smoothness constraint to enhance 3D geometric consistency and stability in decomposition. Extensive experiments demonstrate that Ref-Unlock significantly outperforms classical GS-based reflection methods and achieves competitive results with NeRF-based models, while enabling flexible vision foundation models (VFMs) driven reflection editing. Our method thus offers an efficient and generalizable solution for realistic rendering of reflective scenes. Our code is available at https://ref-unlock.github.io/.
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。
