Deformable Gaussian Splatting (GS) accomplishes photorealistic dynamic 3-D reconstruction from dense multi-view video (MVV) by learning to deform a canonical GS representation. However, in filmmaking, tight budgets can result in sparse camera configurations, which limits state-of-the-art (SotA) methods when capturing complex dynamic features. To address this issue, we introduce an approach that splits the canonical Gaussians and deformation field into foreground and background components using a sparse set of masks for frames at t=0. Each representation is separately trained on different loss functions during canonical pre-training. Then, during dynamic training, different parameters are modeled for each deformation field following common filmmaking practices. The foreground stage contains diverse dynamic features so changes in color, position and rotation are learned. While, the background containing film-crew and equipment, is typically dimmer and less dynamic so only changes in point position are learned. Experiments on 3-D and 2.5-D entertainment datasets show that our method produces SotA qualitative and quantitative results; up to 3 PSNR higher with half the model size on 3-D scenes. Unlike the SotA and without the need for dense mask supervision, our method also produces segmented dynamic reconstructions including transparent and dynamic textures. Code and video comparisons are available online: https://azzarelli.github.io/splatographypage/index.html

翻译：可变形高斯泼溅（Deformable Gaussian Splatting, GS）通过学习变形规范高斯表示，从密集多视角视频（MVV）中实现逼真的动态三维重建。然而在电影制作中，紧张的预算可能导致稀疏相机配置，这限制了当前最优方法（SotA）捕捉复杂动态特征的能力。针对该问题，我们提出一种方法：利用t=0时刻的稀疏掩码集，将规范高斯与变形场分为前景和背景组件。在规范预训练阶段，两种组件分别采用不同损失函数训练。随后在动态训练阶段，遵循电影制作惯例为每个变形场建模不同参数。前景阶段包含丰富的动态特征，因此需学习颜色、位置和旋转的变化；而背景区域（含摄制组与设备）通常较暗且动态性弱，仅需学习点位置变化。在三维和2.5维娱乐数据集上的实验表明，我们的方法在定性及定量结果上均达到最优水平：三维场景中PSNR提升高达3dB，模型尺寸减半。与SotA方法不同，本方法无需密集掩码监督，即可生成包含透明与动态纹理的分割式动态重建。代码与视频对比见：https://azzarelli.github.io/splatographypage/index.html