动态优化高斯点，提速增质重建复杂动态3D场景
GS-DMSR: Dynamic Sensitive Multi-scale Manifold Enhancement for Accelerated High-Quality 3D Gaussian Splatting
- 根据高斯点运动状态自适应调整优化策略
- 合成数据集下实现96帧/秒，训练更快更省存储
- 适合需要实时高质量3D动态重建的研究者
在3D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亟待解决的关键挑战，尤其在复杂动态运动的高精度建模中更为突出。为此，本文提出GS-DMSR方法。通过量化分析高斯属性的动态演化过程，该机制实现了自适应梯度聚焦，能够动态识别高斯模型在运动状态上的显著差异，并对不同重要程度的高斯模型施加差异化的优化策略，从而显著提升模型收敛速度。此外，研究还引入多尺度流形增强模块，通过隐式非线性解码器与显式变形场的协同优化，提升复杂形变场景的建模效率。实验表明，该方法在合成数据集上达到最高96 FPS的帧率，同时有效降低存储开销和训练时间。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。