arXiv:2602.22096v2 Announce Type: replace 
Abstract: 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 \textbf{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.

تم تقديم WeatherCity كإطار جديد لإعادة بناء المشاهد الحضرية ثلاثية الأبعاد وتحرير الطقس، حيث يعالج القيود المفروضة على الطرق الحالية التي تقتصر على تكرار المشاهد المرصودة دون تمكين محاكاة الطقس المتنوعة. يستخدم هذا الإطار نموذج تحرير الصور الموجه بالنص وتمثيل غاوسي للطقس فريد من نوعه لتحسين التحكم في تأثيرات الطقس في البيئات الحضرية.

WeatherCity se ha presentado como un nuevo marco para la reconstrucción de escenas urbanas en 4D y la edición del clima, abordando las limitaciones de los métodos existentes que se limitan a replicar escenas observadas sin permitir simulaciones climáticas diversas. Este marco utiliza un modelo de edición de imágenes guiado por texto y una representación gaussiana climática única para mejorar la controlabilidad de los efectos climáticos en entornos urbanos.

WeatherCity a été introduit comme un nouveau cadre pour la reconstruction de scènes urbaines en 4D et l'édition météorologique, répondant aux limitations des méthodes existantes qui se contentent de reproduire des scènes observées sans permettre des simulations météorologiques variées. Ce cadre utilise un modèle d'édition d'image guidé par texte et une représentation gaussienne météorologique unique pour améliorer la contrôlabilité des effets météorologiques dans les environnements urbains.

WeatherCity has been introduced as a novel framework for 4D urban scene reconstruction and weather editing, addressing the limitations of existing methods that primarily replicate observed scenes without enabling diverse weather simulations. This framework utilizes a text-guided image editing model and a unique weather Gaussian representation to enhance controllability over weather effects in urban environments.