AI 中文总结
本文针对现有EO生成模型的地理空间约束冲突问题，推出90亿参数的GeoCore-9B，采用Flow Matching的DiT与地理空间元数据条件生成，结合地理空间语义对齐损失，在多项EO任务上实现最优性能。
AI 中文摘要
现有的地球观测（EO）生成模型大多依赖对自然图像先验进行微调，这限制了模型的可扩展性，还会引入与地理空间约束相冲突的视角偏差。为解决这一问题，我们推出了GeoCore-9B，这是一款拥有90亿参数的生成基础模型，也是首个完全基于EO数据从头开始训练的同规模模型。与以往的EO基础模型不同，GeoCore-9B构建于基于Flow Matching的扩散Transformer（DiT）之上，能够原生地以文本描述以及连续地理空间元数据（包括地面采样距离、纬度和经度）作为生成条件。为克服该规模模型训练时的收敛问题和空间失准挑战，我们提出了地理空间语义对齐损失，该目标函数从冻结的专业教师网络中提取地球表面结构先验（如地形和城区），在训练过程中对扩散潜轨迹进行约束，且不会增加推理开销。GeoCore-9B在全球规模的Git-10M数据集上进行预训练后，展现出强大的下游通用性。除标准的代理生成任务外，我们还表明GeoCore-9B可有效适配实际EO应用，包括去云、SAR到光学跨模态转换等极具挑战性的任务。大量评估证实，GeoCore-9B在视觉保真度和地理结构准确性两方面均达到了新的最先进性能水平。
英文摘要
Existing generative models for earth observation (EO) predominantly rely on fine-tuning natural image priors, which limits their scalability and introduces perspective biases that conflict with geospatial constraints. To address this, we introduce GeoCore-9B, a 9-billion-parameter generative foundation model, which is the first of its scale to be trained from scratch exclusively on EO data. Unlike previous EO foundation models, GeoCore-9B is built upon a Flow Matching-based Diffusion Transformer (DiT) and natively conditions generation on text descriptions and continuous geospatial metadata, including ground sample distances, latitudes, and longitudes. To overcome the convergence and spatial disorientation challenges of training at this scale, we propose a Geospatial Semantic Alignment loss. This objective distills structural Earth surface priors (e.g., terrain and urban areas) from a frozen specialist teacher network, constraining the diffusion latent trajectory during training without adding inference overhead. Pre-trained on the global-scale Git-10M dataset, GeoCore-9B demonstrates strong downstream versatility. Beyond standard proxy generative tasks, we show that GeoCore-9B can be effectively adapted for practical EO applications, including highly challenging tasks such as cloud removal and SAR-to-optical cross-modal translation. Extensive evaluations confirm that GeoCore-9B establishes new state-of-the-art performance in both visual fidelity and geographic structural accuracy.
CommentsPlease visit our project page at https://kaist-viclab.github.io/GeoCore-9B_site/
