NimbusGS: Unified 3D Scene Reconstruction under Hybrid Weather

TL;DR

NimbusGS is a unified 3D scene reconstruction framework that effectively handles diverse adverse weather conditions by modeling atmospheric effects and transient particles, improving geometry accuracy.

Contribution

It introduces a novel decomposition of weather degradations into static and dynamic components, enabling robust 3D reconstruction under challenging conditions.

Findings

Outperforms existing methods across various weather scenarios.

Disentangles atmospheric effects from transient particles effectively.

Enhances geometry reconstruction quality in degraded environments.

Abstract

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.