SCas4D：结构级联优化提升持久4D新视角合成

SCas4D: Structural Cascaded Optimization for Boosting Persistent 4D Novel View Synthesis

October 8, 2025

作者: Jipeng Lyu, Jiahua Dong, Yu-Xiong Wang

cs.AI

摘要

持久动态场景建模在追踪和新视角合成方面仍面临挑战，主要源于在保持计算效率的同时难以捕捉精确形变。我们提出了SCas4D，一种级联优化框架，它利用3D高斯泼溅中的结构模式来处理动态场景。其核心思想在于现实世界中的形变常呈现层次化模式，即高斯群组共享相似的变换。通过从粗略部件级到精细点级逐步优化形变，SCas4D能在每帧100次迭代内实现收敛，并以仅需现有方法二十分之一的训练迭代次数，产出与之相当的结果。该方法在自监督关节物体分割、新视角合成及密集点追踪任务中也展现了显著成效。

English

Persistent dynamic scene modeling for tracking and novel-view synthesis remains challenging due to the difficulty of capturing accurate deformations while maintaining computational efficiency. We propose SCas4D, a cascaded optimization framework that leverages structural patterns in 3D Gaussian Splatting for dynamic scenes. The key idea is that real-world deformations often exhibit hierarchical patterns, where groups of Gaussians share similar transformations. By progressively refining deformations from coarse part-level to fine point-level, SCas4D achieves convergence within 100 iterations per time frame and produces results comparable to existing methods with only one-twentieth of the training iterations. The approach also demonstrates effectiveness in self-supervised articulated object segmentation, novel view synthesis, and dense point tracking tasks.