This paper proposes an effective Gaussian management framework for high-fidelity scene reconstruction of both appearance and geometry. Unlike recent Gaussian Splatting (GS) pipelines that treat all primitives uniformly during optimization, our framework explicitly manages the attribute activation, representation and pruning of Gaussian. Specifically, our framework first introduces GauSep, a novel densification strategy that selectively activates Gaussian color or normal attributes to alleviate destructive gradient conflicts arising from dual supervision. We further propose GauRep, an adaptive Gaussian representation that dynamically adjusts spherical harmonics (SHs) orders and performs task-decoupled pruning to reduce redundancy at both the individual and global levels. To provide reliable geometric supervision for above mangement process, we additionally introduce CoRe, an regularized surface reconstruction module that distills robust normal fields from an SDF branch to the Gaussian representation through a confidence mechanism. Notably, the proposed Gaussian management is compatible with various reconstruction architectures and can be seamlessly integrated to improve performance while reducing size of the model. Extensive experiments demonstrate that our approach achieves superior or comparable performance in appearance and geometry reconstruction compared with state-of-the-art methods, while using significantly fewer parameters.

翻译：本文提出了一种有效的高斯管理框架，用于实现外观与几何的高保真场景重建。与近期将所有基元统一处理的高斯泼溅（GS）流程不同，我们的框架明确管理高斯的属性激活、表示与剪枝。具体而言，框架首先引入GauSep——一种新型致密化策略，可选择性激活高斯颜色或法线属性，以缓解双重监督引发的破坏性梯度冲突。我们进一步提出GauRep——一种自适应高斯表示方法，能动态调整球谐函数（SHs）阶数，并通过任务解耦剪枝减少个体与全局层面的冗余。为给上述管理过程提供可靠的几何监督，我们还引入CoRe——一种规则化表面重建模块，通过置信度机制将SDF分支的稳健法线场蒸馏至高斯表示。值得注意的是，所提出的高斯管理与多种重建架构兼容，可无缝集成以提升性能并减小模型规模。大量实验表明，与最先进方法相比，本方法在使用显著更少参数的同时，在几何与外观重建上达到更优或相当的性能。