In the field of 3D dynamic scene reconstruction, how to balance model convergence rate and rendering quality has long been a critical challenge that urgently needs to be addressed, particularly in high-precision modeling of scenes with complex dynamic motions. To tackle this issue, this study proposes the GS-DMSR method. By quantitatively analyzing the dynamic evolution process of Gaussian attributes, this mechanism achieves adaptive gradient focusing, enabling it to dynamically identify significant differences in the motion states of Gaussian models. It then applies differentiated optimization strategies to Gaussian models with varying degrees of significance, thereby significantly improving the model convergence rate. Additionally, this research integrates a multi-scale manifold enhancement module, which leverages the collaborative optimization of an implicit nonlinear decoder and an explicit deformation field to enhance the modeling efficiency for complex deformation scenes. Experimental results demonstrate that this method achieves a frame rate of up to 96 FPS on synthetic datasets, while effectively reducing both storage overhead and training time.Our code and data are available at https://anonymous.4open.science/r/GS-DMSR-2212.

翻译：在三维动态场景重建领域，如何平衡模型收敛速度与渲染质量一直是一个亟待解决的关键挑战，尤其是在具有复杂动态运动场景的高精度建模中。为应对这一问题，本研究提出了GS-DMSR方法。该机制通过对高斯属性动态演化过程的定量分析，实现了自适应梯度聚焦，使其能够动态识别高斯模型运动状态的显著差异，进而对具有不同显著程度的高斯模型施加差异化的优化策略，从而显著提升了模型的收敛速度。此外，本研究还集成了一个多尺度流形增强模块，该模块利用隐式非线性解码器与显式变形场的协同优化，提升了对复杂变形场景的建模效率。实验结果表明，该方法在合成数据集上实现了高达96 FPS的帧率，同时有效降低了存储开销与训练时间。我们的代码与数据公开于 https://anonymous.4open.science/r/GS-DMSR-2212。