arXiv 2503.214422025-04-01cs.GRcs.CV

RainyGS：基于物理的Gaussian Splatting的高效降雨合成

RainyGS: Efficient Rain Synthesis with Physically-Based Gaussian Splatting

Peking University（北京大学）；School of Intelligence Science and Technology, Peking University（北京大学智能科学与技术学院）；School of Computer Science, Peking University（北京大学计算机学院）；School of EECS, Peking University（北京大学电子工程与计算机科学学院）；Wangxuan Institute of Computer Technology, Peking University（北京大学王选计算机技术研究院）；State Key Laboratory of Multimedia Information Processing, Peking University（北京大学多媒体信息处理国家重点实验室）；State Key Laboratory of General Artificial Intelligence, Peking University（北京大学通用人工智能国家重点实验室）

Qiyu Dai, Xingyu Ni, Qianfan Shen, Wenzheng Chen, Baoquan Chen, Mengyu Chu

备注：: CVPR 2025

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

提出RainyGS方法，结合基于物理的建模与3DGS渲染框架，在开放世界场景中高效生成逼真且物理准确的动态降雨效果。

摘要：

我们考虑以符合物理规律的方式向野外场景添加动态降雨效果的问题。场景建模的最新进展取得了显著成果，NeRF和3DGS技术成为重建复杂场景的强大工具。然而，尽管这些方法在新视角合成方面很有效，但通常难以处理具有挑战性的场景编辑任务，例如基于物理的降雨模拟。相比之下，传统的基于物理的模拟可以生成逼真的降雨效果，如雨滴和飞溅，但往往依赖熟练的艺术家精心设置高保真场景。这一过程缺乏灵活性和可扩展性，限制了其在更广泛开放世界环境中的适用性。在本工作中，我们提出了RainyGS，这是一种新颖的方法，利用基于物理建模和3DGS两者的优势，在开放世界场景中生成具有物理准确性的逼真动态降雨效果。我们方法的核心是在快速3DGS渲染框架内整合基于物理的雨滴和浅水模拟技术，从而实现对雨滴行为、飞溅和反射的逼真高效模拟。我们的方法支持以超过30 fps的速度合成降雨效果，为用户提供对降雨强度的灵活控制——从小雨到暴雨。我们证明RainyGS在真实世界室外场景和大规模驾驶场景中均表现有效，与最先进的方法相比，能提供更具照片级真实感和物理准确性的降雨效果。项目页面可在https://pku-vcl-geometry.github.io/RainyGS/找到。

英文摘要：

We consider the problem of adding dynamic rain effects to in-the-wild scenes in a physically-correct manner. Recent advances in scene modeling have made significant progress, with NeRF and 3DGS techniques emerging as powerful tools for reconstructing complex scenes. However, while effective for novel view synthesis, these methods typically struggle with challenging scene editing tasks, such as physics-based rain simulation. In contrast, traditional physics-based simulations can generate realistic rain effects, such as raindrops and splashes, but they often rely on skilled artists to carefully set up high-fidelity scenes. This process lacks flexibility and scalability, limiting its applicability to broader, open-world environments. In this work, we introduce RainyGS, a novel approach that leverages the strengths of both physics-based modeling and 3DGS to generate photorealistic, dynamic rain effects in open-world scenes with physical accuracy. At the core of our method is the integration of physically-based raindrop and shallow water simulation techniques within the fast 3DGS rendering framework, enabling realistic and efficient simulations of raindrop behavior, splashes, and reflections. Our method supports synthesizing rain effects at over 30 fps, offering users flexible control over rain intensity -- from light drizzles to heavy downpours. We demonstrate that RainyGS performs effectively for both real-world outdoor scenes and large-scale driving scenarios, delivering more photorealistic and physically-accurate rain effects compared to state-of-the-art methods. Project page can be found at https://pku-vcl-geometry.github.io/RainyGS/

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。