置信度引导的多尺度聚合用于稀疏视角高分辨率三维高斯泼溅
Confidence-Guided Multi-Scale Aggregation for Sparse-View High-Resolution 3D Gaussian Splatting
把输入分辨率当作稀疏视角 3DGS 的一个可控变量来量化其稳定性与细节之间的权衡，并用跨尺度一致性加权聚合把高分辨率重建锚定到低分辨率的稳定几何上；这套由粗到细的多尺度聚合与伪视角正则化可直接嵌入现有 3DGS 管线，用于缓解高分辨率下的漂浮伪影与过拟合。
原文依据 we identify and quantify a trade-off: lower-resolution inputs facilitate stable global geometry reconstruction, whereas higher-resolution inputs enable finer detail recovery but introduce high-frequency artifacts and instability
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论稀疏视角三维高斯泼溅（3DGS）利用稀疏输入视角以三维高斯表示重建场景。然而该方法容易过拟合，且这一问题在更高分辨率下会被加剧，因为维度的扩大会放大漂浮伪影与重建歧义。本文对稀疏视角条件及不同输入分辨率下的 3DGS 展开系统性研究。已有工作忽视了分辨率作为稀疏视角性能关键因素的作用，而我们识别并量化了一组权衡：较低分辨率输入有助于稳定的全局几何重建，而较高分辨率输入能够恢复更精细的细节，但会引入高频伪影与不稳定性。基于这一发现，我们进一步提出 CAGS，即置信度引导的多尺度聚合，通过由粗到细的层次化优化过程重建场景。该方法采用基于匹配的加权聚合策略，将高分辨率重建锚定到稳定的结构先验上，并通过跨尺度一致性滤除噪声；同时采用多尺度伪视角正则化来细化局部细节而不放大噪声。在 LLFF 与 Mip-NeRF360 数据集上的大量实验表明，CAGS 显著优于现有方法，尤其是在苛刻的高分辨率条件下。此外，我们的范式可以无缝集成到其他基于 3DGS 的管线中，从而将该领域从低分辨率重建扩展到真实世界稀疏视角约束下的高保真输出。
英文原文摘要 1579 字符
Sparse-view 3D Gaussian Splatting (3DGS) reconstructs scenes using 3D Gaussians from sparse input views. Yet, this method is prone to overfitting, which is exacerbated at higher resolutions as the expanded dimensionality amplifies floating artifacts and reconstruction ambiguities. In this paper, we present a systematic study of 3DGS under sparse-view conditions and varying input resolutions. While prior work has overlooked resolution as a key factor in sparse-view performance, we identify and quantify a trade-off: lower-resolution inputs facilitate stable global geometry reconstruction, whereas higher-resolution inputs enable finer detail recovery but introduce high-frequency artifacts and instability. Building on this insight, we further propose CAGS, a Confidence-Guided Multi-Scale Aggregation that reconstructs scenes through a coarse-to-fine hierarchical optimization process. Our approach employs a matching-based weighting aggregation strategy to anchor high-resolution reconstructions to stabilize structural priors and filtering noise through cross-scale consistency, and a multi-scale pseudo-view regularization to refine local details without amplifying noise. Extensive experiments on the LLFF and Mip-NeRF360 datasets demonstrate that CAGS significantly outperforms existing methods, particularly under demanding high-resolution conditions. Moreover, our paradigm can be seamlessly integrated into other 3DGS-based pipelines, thereby extending the field from low-resolution reconstructions to high-fidelity outputs under real-world sparse-view constraints.