面向无约束场景重建的可扩展性增强型微宏观高斯泼溅
Micro-macro Gaussian Splatting with Enhanced Scalability for Unconstrained Scene Reconstruction
AI总结：
针对无约束图像3D场景重建的外观差异难题，提出SMW-GS方法，通过微宏观投影、小波采样及大规模场景分配策略，在重建质量与可扩展性上优于现有方法，尤其适配光照复杂的大规模城市场景。
摘要：
从无约束图像集合重建3D场景因外观存在差异，面临着严峻挑战。本文提出了可扩展微宏观小波高斯泼溅（Scalable Micro-macro Wavelet-based Gaussian Splatting，SMW-GS），这是一种将场景表示分解为全局分量、细化分量和本征分量，以提升多尺度下3D重建效果的新方法。SMW-GS包含以下创新点：微宏观投影，可让高斯点采样多尺度细节，提升采样多样性；基于小波的采样，利用频域信息细化特征表示，以更好地捕捉复杂的场景外观。为实现可扩展性，我们进一步提出了大规模场景提升策略，该策略通过最大化相机视角对高斯点的贡献，将相机视角最优分配给场景分区，即便在广阔环境中也能实现一致的高质量重建。大量实验表明，SMW-GS在重建质量和可扩展性上均显著优于现有方法，在存在挑战性光照变化的大规模城市场景中表现尤为突出。项目地址：https://github.com/Kidleyh/SMW-GS。
英文摘要：
Reconstructing 3D scenes from unconstrained image collections poses significant challenges due to variations in appearance. In this paper, we propose Scalable Micro-macro Wavelet-based Gaussian Splatting (SMW-GS), a novel method that enhances 3D reconstruction across diverse scales by decomposing scene representations into global, refined, and intrinsic components. SMW-GS incorporates the following innovations: Micro-macro Projection, which enables Gaussian points to sample multi-scale details with improved diversity; and Wavelet-based Sampling, which refines feature representations using frequency-domain information to better capture complex scene appearances. To achieve scalability, we further propose a large-scale scene promotion strategy, which optimally assigns camera views to scene partitions by maximizing their contributions to Gaussian points, achieving consistent and high-quality reconstructions even in expansive environments. Extensive experiments demonstrate that SMW-GS significantly outperforms existing methods in both reconstruction quality and scalability, particularly excelling in large-scale urban environments with challenging illumination variations. Project is available at https://github.com/Kidleyh/SMW-GS.
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。
