从飞行到洞察：基于高斯泼溅与语言引导分割的航空巡检语义三维重建
From Flight to Insight: Semantic 3D Reconstruction for Aerial Inspection via Gaussian Splatting and Language-Guided Segmentation
AI总结：
本文提出一种基于无人机和三维高斯泼溅的语义重建流程，结合语言引导分割，实现航空巡检中的灵活交互与场景理解。
摘要：
高保真三维重建对于航空巡检任务至关重要，例如基础设施监测、结构评估和环境勘测。虽然传统摄影测量技术能够实现几何建模，但它们缺乏语义可解释性，限制了其在自动化巡检工作流程中的有效性。神经渲染和三维高斯泼溅（3DGS）的最新进展提供了高效、逼真的重建，但同样缺乏场景级理解。在本工作中，我们提出了一种基于无人机（UAV）的流程，将Feature-3DGS扩展用于语言引导的三维分割。我们利用基于LSeg的特征场与CLIP嵌入，根据语言提示生成热图。对这些热图进行阈值处理以产生粗略分割，然后将得分最高的点作为提示输入SAM或SAM2，以在新视角渲染上进行精细的二维分割。我们的结果展示了各种特征场骨干网络（CLIP-LSeg、SAM、SAM2）在捕捉大规模户外环境中有意义结构方面的优势与局限。我们证明，这种混合方法能够实现对逼真三维重建的灵活、语言驱动的交互，为语义航空巡检和场景理解开辟了新的可能性。
英文摘要：
High-fidelity 3D reconstruction is critical for aerial inspection tasks such as infrastructure monitoring, structural assessment, and environmental surveying. While traditional photogrammetry techniques enable geometric modeling, they lack semantic interpretability, limiting their effectiveness for automated inspection workflows. Recent advances in neural rendering and 3D Gaussian Splatting (3DGS) offer efficient, photorealistic reconstructions but similarly lack scene-level understanding. In this work, we present a UAV-based pipeline that extends Feature-3DGS for language-guided 3D segmentation. We leverage LSeg-based feature fields with CLIP embeddings to generate heatmaps in response to language prompts. These are thresholded to produce rough segmentations, and the highest-scoring point is then used as a prompt to SAM or SAM2 for refined 2D segmentation on novel view renderings. Our results highlight the strengths and limitations of various feature field backbones (CLIP-LSeg, SAM, SAM2) in capturing meaningful structure in large-scale outdoor environments. We demonstrate that this hybrid approach enables flexible, language-driven interaction with photorealistic 3D reconstructions, opening new possibilities for semantic aerial inspection and scene understanding.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
