研究人员开发了 GMBFormer，这是一个新的基于 Transformer 的框架，旨在改进从超高分辨率图像中提取城市绿地。该模型利用归一化植被指数 (NDVI) 数据作为物理信息门，选择性地将植被描述符纳入全局记忆库。通过采用记忆介导的交叉注意力进行原型检索，GMBFormer 旨在克服传统逐块分析的局限性，并改进空间分离区域之间的语义重用。 AI
影响 增强城市规划和环境监测的遥感能力。
排序理由 该集群包含一篇详细介绍新模型及其实验结果的研究论文。
AI 生成摘要 · Google Gemini · 来自 3 个来源。 我们如何撰写摘要 →
Urban green-space extraction from ultra-high-resolution (UHR) imagery is commonly performed patch by patch, which limits semantic reuse among spatially separated but visually similar vegetation patterns. Directly injecting the Normalized Difference Vegetation Index (NDVI) into re…
arXiv:2606.06363v1 Announce Type: new Abstract: Urban green-space extraction from ultra-high-resolution (UHR) imagery is commonly performed patch by patch, which limits semantic reuse among spatially separated but visually similar vegetation patterns. Directly injecting the Norma…
Urban green-space extraction from ultra-high-resolution (UHR) imagery is commonly performed patch by patch, which limits semantic reuse among spatially separated but visually similar vegetation patterns. Directly injecting the Normalized Difference Vegetation Index (NDVI) into re…