SkySplat: 多时序稀疏卫星图像上的通用3D高斯点云生成
SkySplat: Generalizable 3D Gaussian Splatting from Multi-Temporal Sparse Satellite Images
AI总结：
SkySplat通过整合RPC模型提升稀疏卫星图像的3D重建效率，采用自监督框架和跨自我一致性模块，实现86倍速度提升和更精确的重建结果。
摘要：
从稀疏视图卫星图像中进行三维场景重建是一项长期且具有挑战性的任务。尽管3D高斯点云生成（3DGS）及其变种因其高效性而受到关注，但现有方法仍无法适应卫星图像，因为它们与有理多项式系数（RPC）模型不兼容且泛化能力有限。最近的通用3DGS方法显示出潜力，但在多时序稀疏卫星图像上表现不佳，原因是几何约束有限、瞬时物体和辐射不一致。为解决这些问题，我们提出了SkySplat，一种新颖的自监督框架，将RPC模型整合到通用3DGS流程中，使稀疏几何线索更有效地用于重建。SkySplat仅依赖RGB图像和辐射鲁棒的相对高度监督，从而无需真实高度图。关键组件包括跨自我一致性模块（CSCM），通过一致性掩码减轻瞬时物体干扰，以及多视图一致性聚合策略，优化重建结果。与单场景优化方法相比，SkySplat在EOGS上实现了86倍的速度提升，精度更高。它还优于通用3DGS基线，显著降低了DFC19数据集上的MAE值，从13.18米降至1.80米，并在MVS3D基准上展示了强大的跨数据集泛化能力。该方法可在https://github.com/NanCheng2001/SkySplat-main上获取。
英文摘要：
Three-dimensional scene reconstruction from sparse-view satellite images is a long-standing and challenging task. While 3D Gaussian Splatting (3DGS) and its variants have recently attracted attention for its high efficiency, existing methods remain unsuitable for satellite images due to incompatibility with rational polynomial coefficient (RPC) models and limited generalization capability. Recent advances in generalizable 3DGS approaches show potential, but they perform poorly on multi-temporal sparse satellite images due to limited geometric constraints, transient objects, and radiometric inconsistencies. To address these limitations, we propose SkySplat, a novel self-supervised framework that integrates the RPC model into the generalizable 3DGS pipeline, enabling more effective use of sparse geometric cues for improved reconstruction. SkySplat relies only on RGB images and radiometric-robust relative height supervision, thereby eliminating the need for ground-truth height maps. Key components include a Cross-Self Consistency Module (CSCM), which mitigates transient object interference via consistency-based masking, and a multi-view consistency aggregation strategy that refines reconstruction results. Compared to per-scene optimization methods, SkySplat achieves an 86 times speedup over EOGS with higher accuracy. It also outperforms generalizable 3DGS baselines, reducing MAE from 13.18 m to 1.80 m on the DFC19 dataset significantly, and demonstrates strong cross-dataset generalization on the MVS3D benchmark. The is available at https://github.com/NanCheng2001/SkySplat-main
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。
