发表机构
Inria, Université Côte d’Azur; EPFL（法国蔚蓝海岸大学 - 法国国家信息与自动化研究所; 洛桑联邦理工学院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
研究针对无序输入的辐射场捕获，提出利用视觉位置识别模型等实现快速匹配找关键帧，结合GPU优化等进行局部重建，再用基于聚类方法实现回环闭合，引入渐进层次结构处理大场景，提供具全局一致性的即时反馈3DGS重建。
AI 中文摘要
3D高斯点云（3DGS）已成为捕获场景重建和实时渲染的首选方法。为了获得高质量视觉效果的场景，通常将连续图像序列与无序拍摄相结合以实现更好的场景覆盖。运动结构（SfM）可以重建此类捕获，但需要所有图像可用且计算成本高。增量重建方法虽能提供即时反馈，但无法处理无序捕获。我们提供了首个针对此类辐射场捕获的即时反馈解决方案，具有全局一致性。首先通过重新利用视觉位置识别模型和共视性图，引入一种在无序序列中快速匹配的方法，并找到高度连接的关键帧，即便对于有序序列也能提高质量。展示了这些步骤与GPU优化及高斯基元放置如何实现快速局部重建。接着引入一种基于聚类的新方法，利用共视性图提供无需顺序输入的高效回环闭合。最后，引入渐进层次结构以处理大场景，使方法能扩展到大型环境且不降低效率。结果表明，在多个数据集上，我们能为数千张输入图像提供具有良好视觉质量的即时反馈3DGS重建。
英文摘要
3D Gaussian Splatting (3DGS) has become the method of choice for reconstructing and real-time rendering of captured scenes. To capture a scene with good visual quality, continuous image sequences are usually combined with out-of-order shots for better scene coverage. Structure from motion can reconstruct such captures, but only after they are all available and often with high computational cost. Incremental reconstruction methods -- often derived from SLAM solutions -- provide immediate feedback, but cannot handle the out-of-order capture we require. We provide the first immediate feedback solution for such radiance field capture that provides global consistency. We first introduce a method for fast matching in out-of-order sequences, by repurposing visual place recognition models and a covisibility graph, and provide an efficient way to find highly connected keyframes, improving quality even for ordered sequences. We show how these steps -- together with GPU optimization and careful Gaussian primitive placement -- provide fast local reconstruction, in our challenging radiance field reconstruction case. We then introduce a novel cluster-based method, again using the covisibility graph, to provide efficient loop closure that does not require sequential input. Finally, to handle large scenes in our context, we introduce a progressive hierarchy that allows our method to scale to large environments, without compromising efficiency. Our results show we provide immediate feedback 3DGS reconstruction with good visual quality in several datasets, with up to thousands of input images.
Journal refSIGGRAPH Conference Papers 2026
