统一重建恶劣天气下的3D场景，效果优于专用方法。
NimbusGS: Unified 3D Scene Reconstruction under Hybrid Weather
- 将天气退化分解为全局透射场和视图特有残差
- 在极端能见度下仍能稳定重建高质量几何结构
- 适合需要跨天气泛化的3D重建应用
我们提出NimbusGS，一种统一框架，用于从多视角、受多种混合恶劣天气影响的输入中重建高质量3D场景。不同于仅针对特定天气的方法，NimbusGS通过建模天气的双重特性来解决更广泛的泛化挑战：连续且视图一致的介质会衰减光线，动态且视图相关的粒子则引发散射与遮挡。为捕捉这一结构，我们将退化分解为全局透射场和每视图的颗粒残差。透射场表示各视图共享的静态大气效应，而残差则建模每个输入独有的瞬态干扰。为在严重能见度退化下实现稳定的几何学习，我们引入基于几何引导的梯度缩放机制，缓解自监督优化中3D高斯表示的梯度不平衡问题。该物理驱动的公式使NimbusGS能够解耦复杂退化，同时保留场景结构，在多样且严苛的天气条件下表现优于任务专用方法。代码已开源：https://github.com/lyy-ovo/NimbusGS。
原文摘要 · Abstract (English)
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. Code is available at https://github.com/lyy-ovo/NimbusGS.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。