提升三维高斯散射泛化能力的频率自适应锐度正则化方法

摘要

尽管三维高斯泼溅（3DGS）在多数配置中表现卓越，但在稀疏观测数据的少样本场景下，由于对稀疏观测的过拟合，其在新视角下的泛化能力不足。我们从机器学习视角重新审视3DGS的优化过程，将新视角合成问题定义为对未见过视角的泛化问题——这一研究方向尚未被充分探索。我们提出频率自适应锐度正则化（FASR），通过重构3DGS的训练目标函数，引导3DGS收敛至具有更优泛化能力的解。虽然锐度感知最小化（SAM）方法同样通过降低损失景观的锐度来提升分类模型的泛化能力，但由于任务差异，直接将其应用于3DGS会产生次优结果。具体而言，过强的正则化会阻碍高频细节重建，而减弱正则化强度又会导致锐度惩罚不足。为此，我们通过反映图像的局部频率特性来设定正则化权重及估计局部锐度时的邻域半径。该方法既能有效避免新视角下的漂浮伪影，又能重建SAM容易过度平滑的精细细节。在多种配置的数据集上，我们的方法持续提升了各类基线的性能。代码将在https://bbangsik13.github.io/FASR发布。

English

Despite 3D Gaussian Splatting (3DGS) excelling in most configurations, it lacks generalization across novel viewpoints in a few-shot scenario because it overfits to the sparse observations. We revisit 3DGS optimization from a machine learning perspective, framing novel view synthesis as a generalization problem to unseen viewpoints-an underexplored direction. We propose Frequency-Adaptive Sharpness Regularization (FASR), which reformulates the 3DGS training objective, thereby guiding 3DGS to converge toward a better generalization solution. Although Sharpness-Aware Minimization (SAM) similarly reduces the sharpness of the loss landscape to improve generalization of classification models, directly employing it to 3DGS is suboptimal due to the discrepancy between the tasks. Specifically, it hinders reconstructing high-frequency details due to excessive regularization, while reducing its strength leads to under-penalizing sharpness. To address this, we reflect the local frequency of images to set the regularization weight and the neighborhood radius when estimating the local sharpness. It prevents floater artifacts in novel viewpoints and reconstructs fine details that SAM tends to oversmooth. Across datasets with various configurations, our method consistently improves a wide range of baselines. Code will be available at https://bbangsik13.github.io/FASR.

提升三维高斯散射泛化能力的频率自适应锐度正则化方法

Frequency-Adaptive Sharpness Regularization for Improving 3D Gaussian Splatting Generalization

摘要

Support