Beyond Static Gaussians: An Empirical Investigation of Architectural Paradigms for Dynamic 3D Scene Reconstruction
For researchers in dynamic 3D scene reconstruction, this paper provides a systematic comparison highlighting the trade-off between quality/compactness and speed, guiding future method selection and development.
This paper categorizes dynamic 3D Gaussian Splatting methods into structure-guided and gaussian-centric paradigms, evaluating them on the D-NeRF benchmark. Structure-guided methods achieve superior reconstruction fidelity and compact models, while gaussian-centric methods offer higher rendering speeds but with greater quality variability and storage overhead.
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.