对比两类动态3D重建方法，发现速度与质量难以兼得。
Beyond Static Gaussians: An Empirical Investigation of Architectural Paradigms for Dynamic 3D Scene Reconstruction
- 分两类方法：用辅助结构建模变化，或直接在点上编码动态。
- 结构引导法精度高、模型小，点中心法渲染快但质量波动大。
- 适合关注实时渲染或追求高保真的研究者参考。
基于3D高斯喷溅（3DGS）的动态场景重建已成为表征演变环境的有力方法，但理解不同方法间的权衡仍至关重要。本文对动态3DGS方法进行了全面分析，将其分为两大范式：结构引导方法利用变形场、标准空间、网格等辅助表示来建模时间变化；高斯中心方法则通过连续函数或4D表示直接在几何原语中编码动态。我们在D-NeRF基准上评估了两类代表方法。结果表明，结构引导方法在重建保真度和模型紧凑性上表现更优，而高斯中心方法则展现出显著更高的渲染速度，支持实时性能，尽管存在质量波动较大且存储开销可能较高的问题。该分析揭示了重建质量/紧凑性与渲染速度之间的根本权衡，为未来动态场景重建的研究与应用提供了指导。
原文摘要 · Abstract (English)
Dynamic scene reconstruction via 3D Gaussian Splatting (3DGS) has emerged as a compelling approach for representing evolving environments, yet understanding trade-offs between methodologies remains crucial. This paper presents a comprehensive analysis of dynamic 3DGS methods, categorizing them into two paradigms: structure-guided methods employing auxiliary representations (deformation fields, canonical spaces, grids) to model temporal changes, and gaussian-centric methods encoding dynamics directly into primitives via continuous functions or 4D representations. We evaluate representative methods from both paradigms on the D-NeRF benchmark. Our findings reveal that structure-guided methods achieve superior reconstruction fidelity and compact model sizes, while gaussian-centric approaches demonstrate significantly higher rendering speeds enabling real-time performance, though with greater quality variability and potentially substantial storage overhead. This analysis highlights a fundamental trade-off between reconstruction quality/compactness versus rendering speed, providing insights to guide future research and application development in dynamic scene reconstruction.
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。