WeatherCity：可控多天气变换的城市场景重建
WeatherCity: Urban Scene Reconstruction with Controllable Multi-Weather Transformation
把天气编辑从图像级搬到 4D 高斯场景级：用共享场景特征加天气专属解码器构造天气高斯表示，并用内容一致性优化保证跨天气几何一致，可直接用于自动驾驶闭环仿真中的多天气数据合成。
原文依据 we introduce a novel weather Gaussian representation based on shared scene features and dedicated weather-specific decoders
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论可编辑的高保真 4D 场景对自动驾驶至关重要，因为它们可用于端到端训练与闭环仿真。然而，现有的重建方法主要局限于复现观测到的场景，缺乏多样天气模拟的能力。而图像级天气编辑方法往往会引入场景伪影，且对天气效果的可控性较差。为解决这些局限，我们提出 WeatherCity，一个用于 4D 城市场景重建与天气编辑的新框架。具体而言，我们利用文本引导的图像编辑模型实现对图像天气背景的灵活编辑。为应对多天气建模的挑战，我们引入一种新的天气高斯表示，它基于共享场景特征与各天气专属解码器。该表示进一步通过内容一致性优化得到增强，从而确保不同天气条件下的连贯建模。此外，我们设计了一个物理驱动模型，通过粒子与运动模式模拟动态天气效果。在多个数据集和多种场景上的大量实验表明，WeatherCity 在 4D 重建与天气编辑中实现了灵活的可控性、高保真度与时序一致性。我们的框架不仅能够对天气条件（如小雨和大雪）进行细粒度控制，还支持场景内的物体级操作。代码已发布于 https://github.com/IRMVLab/WeatherCity。
英文原文摘要 1558 字符
Editable high-fidelity 4D scenes are crucial for autonomous driving, as they can be applied to end-to-end training and closed-loop simulation. However, existing reconstruction methods are primarily limited to replicating observed scenes and lack the capability for diverse weather simulation. While image-level weather editing methods tend to introduce scene artifacts and offer poor controllability over the weather effects. To address these limitations, we propose WeatherCity, a novel framework for 4D urban scene reconstruction and weather editing. Specifically, we leverage a text-guided image editing model to achieve flexible editing of image weather backgrounds. To tackle the challenge of multi-weather modeling, we introduce a novel weather Gaussian representation based on shared scene features and dedicated weather-specific decoders. This representation is further enhanced with a content consistency optimization, ensuring coherent modeling across different weather conditions. Additionally, we design a physics-driven model that simulates dynamic weather effects through particles and motion patterns. Extensive experiments on multiple datasets and various scenes demonstrate that WeatherCity achieves flexible controllability, high fidelity, and temporal consistency in 4D reconstruction and weather editing. Our framework not only enables fine-grained control over weather conditions (e.g., light rain and heavy snow) but also supports object-level manipulation within the scene. Codes are released at https://github.com/IRMVLab/WeatherCity.