用高斯点云加速遥感多视角分割，实时渲染同时出图像和语义图。
Efficient Semantic Splatting for Remote Sensing Multi-view Segmentation
- 将点云的RGB与语义特征投影到图像平面，一次渲染完成图像与分割。
- 在遥感数据上实现低延迟，优化效率显著提升。
- 用SAM2生成边界伪标签，双层损失增强视图一致性。
本文提出一种基于高斯点云的新型语义拼贴方法，实现高效低延迟的遥感多视角分割。该方法将点云的RGB属性与语义特征投影至图像平面，同步渲染出RGB图像与语义分割结果。利用点云的显式结构及一次性渲染策略，在优化与渲染阶段大幅提升效率。此外，采用SAM2为边界区域生成伪标签，并引入二维特征图与三维空间层面的双层聚合损失，有效提升视图一致性和空间连续性。
原文摘要 · Abstract (English)
In this paper, we propose a novel semantic splatting approach based on Gaussian Splatting to achieve efficient and low-latency. Our method projects the RGB attributes and semantic features of point clouds onto the image plane, simultaneously rendering RGB images and semantic segmentation results. Leveraging the explicit structure of point clouds and a one-time rendering strategy, our approach significantly enhances efficiency during optimization and rendering. Additionally, we employ SAM2 to generate pseudo-labels for boundary regions, which often lack sufficient supervision, and introduce two-level aggregation losses at the 2D feature map and 3D spatial levels to improve the view-consistent and spatial continuity.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。