IR-HGP：借助生成先验的高光照场景物理感知高斯逆渲染
IR-HGP: Physically-Aware Gaussian Inverse Rendering for High-Illumination Scenes via Generative Priors
将生成式光照场先验与物理可见性分解引入 3DGS 逆渲染，为高光/强反射场景下的材质-光照解耦与可重光照资产重建提供了可复用方案，可直接用于重光照与新视角合成管线。
原文依据 Applying 3D Gaussian Splatting to inverse rendering, especially for relightable assets under high-illuminance conditions, remains challenging.
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论将三维高斯泼溅应用于逆渲染，尤其是在高光照条件下重建可重光照资产，仍然具有挑战性。强烈的镜面高光与复杂反射使材质与光照的解耦变得困难，往往导致阴影被烘焙进材质并丢失镜面细节。为解决这一问题，我们提出 IR-HGP，一个通过三个协同模块实现稳健解耦的框架：首先，混合可见性分解模块保证物理可见性一致；其次，生成式光照场先验模块推断细节丰富的高动态范围环境光照；最后，物理感知辐射校正模块稳定优化过程并缓解光照伪影。我们的框架在材质恢复与重光照上达到当前最优性能，在具有挑战性的光照条件下优于现有方法。它能够实时重建反射表面随视角变化的“闪亮”外观，超越了以往基于三维高斯泼溅的逆渲染方法的局限。
英文原文摘要 1035 字符
Applying 3D Gaussian Splatting to inverse rendering, especially for relightable assets under high-illuminance conditions, remains challenging. Strong specular highlights and complex reflections complicate material-light disentanglement, often baking in shadows and losing specular detail. To address this, we introduce IR-HGP, a framework that achieves robust disentanglement using three synergistic modules: First, a Hybrid Visibility Decomposition module ensures physical visibility consistency. Second, a Generative Illumination Field Prior module infers detailed and high-dynamic range environmental lighting. Finally, a Physics-Aware Radiance Correction module stabilizes optimization and mitigates illumination artifacts. Our framework achieves SOTA material recovery and relighting performance, outperforming existing methods under challenging illumination conditions. It reconstructs the view-dependent "shiny" appearance of reflective surfaces in real time, surpassing the limits of prior 3DGS-based inverse rendering methods.