NimbusGS：混合天气条件下的统一三维场景重建
NimbusGS: Unified 3D Scene Reconstruction under Hybrid Weather
把恶劣天气退化拆成跨视角一致的全局透射场与逐视角的粒子残差，并配合几何引导的梯度缩放，使 3DGS 在低能见度多视角输入下仍能稳定学出几何，可直接迁移到雨雾雪混合场景的重建与新视角合成。
原文依据 a geometry-guided gradient scaling mechanism that mitigates gradient imbalance during the self-supervised optimization of 3D Gaussian representations
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论本文提出 NimbusGS，一个用于从多样且混合的恶劣天气条件下采集的退化多视角输入中重建高质量三维场景的统一框架。现有方法通常针对特定天气类型，而 NimbusGS 通过建模天气的双重性质来应对更广泛的泛化挑战：天气既是一种连续、跨视角一致并衰减光线的介质，又包含导致散射与遮挡的动态、视角相关的粒子。为刻画这一结构，我们将退化分解为全局透射场与逐视角粒子残差。透射场表示跨视角共享的静态大气效应，残差则建模每个输入所独有的瞬态扰动。为在严重能见度退化下实现稳定的几何学习，我们引入几何引导的梯度缩放机制，缓解三维高斯表示自监督优化过程中的梯度不平衡问题。这一具有物理依据的建模使 NimbusGS 能够解耦复杂退化并保持场景结构，从而获得更优的几何重建，并在多样且具有挑战性的天气条件下优于针对特定任务的方法。
英文原文摘要 1236 字符
We present NimbusGS, a unified framework for reconstructing high-quality 3D scenes from degraded multi-view inputs captured under diverse and mixed adverse weather conditions. Unlike existing methods that target specific weather types, NimbusGS addresses the broader challenge of generalization by modeling the dual nature of weather: a continuous, view-consistent medium that attenuates light, and dynamic, view-dependent particles that cause scattering and occlusion. To capture this structure, we decompose degradations into a global transmission field and per-view particulate residuals. The transmission field represents static atmospheric effects shared across views, while the residuals model transient disturbances unique to each input. To enable stable geometry learning under severe visibility degradation, we introduce a geometry-guided gradient scaling mechanism that mitigates gradient imbalance during the self-supervised optimization of 3D Gaussian representations. This physically grounded formulation allows NimbusGS to disentangle complex degradations while preserving scene structure, yielding superior geometry reconstruction and outperforming task-specific methods across diverse and challenging weather conditions.