卫星影像直接重建，精度与速度双提升
EOGS++: Earth Observation Gaussian Splatting with Internal Camera Refinement and Direct Panchromatic Rendering
- 基于光流嵌入相机位姿优化，无需外部工具
- 在两个数据集上建筑均方误差从1.33降至1.19
- 支持原始全色图像直接处理，适合遥感应用
最近，3D高斯点阵被引入地球观测领域，作为NeRF的有力替代方案，在显著缩短训练时间的同时实现了具有竞争力的重建质量。本文在此基础上提出EOGS++，一种专为卫星影像设计的新方法，可直接处理高分辨率原始全色数据，无需外部预处理。通过融合光流技术，将束调整嵌入训练过程，避免依赖外部优化工具，同时提升了相机位姿估计精度。此外，还引入了早停策略和TSDF后处理等改进，进一步提升了重建清晰度与几何准确性。在IARPA 2016和DFC2019数据集上的实验表明，EOGS++在重建质量与效率方面达到当前最优水平，优于原EOGS及其它基于NeRF的方法，同时保持高斯点阵的计算优势。模型在建筑区域的平均绝对误差从1.33降低至1.19。
原文摘要 · Abstract (English)
Recently, 3D Gaussian Splatting has been introduced as a compelling alternative to NeRF for Earth observation, offering competitive reconstruction quality with significantly reduced training times. In this work, we extend the Earth Observation Gaussian Splatting (EOGS) framework to propose EOGS++, a novel method tailored for satellite imagery that directly operates on raw high-resolution panchromatic data without requiring external preprocessing. Furthermore, leveraging optical flow techniques we embed bundle adjustment directly within the training process, avoiding reliance on external optimization tools while improving camera pose estimation. We also introduce several improvements to the original implementation, including early stopping and TSDF post-processing, all contributing to sharper reconstructions and better geometric accuracy. Experiments on the IARPA 2016 and DFC2019 datasets demonstrate that EOGS++ achieves state-of-the-art performance in terms of reconstruction quality and efficiency, outperforming the original EOGS method and other NeRF-based methods while maintaining the computational advantages of Gaussian Splatting. Our model demonstrates an improvement from 1.33 to 1.19 mean MAE errors on buildings compared to the original EOGS models
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。