PixDLM：面向无人机推理分割的双路径多模态语言模型
PixDLM: A Dual-Path Multimodal Language Model for UAV Reasoning Segmentation
把思维链问答监督与像素级分割输出耦合进一个多模态语言模型，为高分辨率斜视无人机影像提供可复用的推理分割基线；其按空间、属性、场景三级组织语义需求的思路，可直接迁移到其他需要复杂推理的开放词表分割设定。
原文依据 we introduce PixDLM, a simple yet effective pixel-level multimodal language model that serves as a unified baseline for this task
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论推理分割近来已从地面场景扩展到遥感影像，但无人机数据带来了独特挑战，包括倾斜视角、超高分辨率和极端的尺度变化。为解决这些问题，我们正式定义了无人机推理分割任务，并将其语义需求组织为三个维度：空间推理、属性推理和场景级推理。基于这一形式化定义，我们构建了 DRSeg，一个面向无人机推理分割的大规模基准，包含 1 万张高分辨率航空影像，并配有覆盖全部三类推理的思维链问答监督。作为该基准的配套，我们提出 PixDLM，一个简单而有效的像素级多模态语言模型，可作为该任务的统一基线。在 DRSeg 上的实验确立了强有力的基线结果，并凸显了无人机推理分割的独特挑战，为未来研究提供了坚实基础。所有数据集、模型和代码均可在 https://github.com/XIEFOX/PixDLM 获取。
英文原文摘要 1046 字符
Reasoning segmentation has recently expanded from ground-level scenes to remote-sensing imagery, yet UAV data poses distinct challenges, including oblique viewpoints, ultra-high resolutions, and extreme scale variations. To address these issues, we formally define the UAV Reasoning Segmentation task and organize its semantic requirements into three dimensions: Spatial, Attribute, and Scene-level reasoning. Based on this formulation, we construct DRSeg, a large-scale benchmark for UAV reasoning segmentation, containing 10k high-resolution aerial images paired with Chain-of-Thought QA supervision across all three reasoning types. As a benchmark companion, we introduce PixDLM, a simple yet effective pixel-level multimodal language model that serves as a unified baseline for this task. Experiments on DRSeg establish strong baseline results and highlight the unique challenges of UAV reasoning segmentation, providing a solid foundation for future research. All datasets, models, and code are available at https://github.com/XIEFOX/PixDLM.