Laplacian Analysis Meets Dynamics Modelling: Gaussian Splatting for 4D Reconstruction
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866911095350886400 |
|---|---|
| author | Zhou, Yifan Zhao, Beizhen Wu, Pengcheng Wang, Hao |
| author_facet | Zhou, Yifan Zhao, Beizhen Wu, Pengcheng Wang, Hao |
| contents | While 3D Gaussian Splatting (3DGS) excels in static scene modeling, its extension to dynamic scenes introduces significant challenges. Existing dynamic 3DGS methods suffer from either over-smoothing due to low-rank decomposition or feature collision from high-dimensional grid sampling. This is because of the inherent spectral conflicts between preserving motion details and maintaining deformation consistency at different frequency. To address these challenges, we propose a novel dynamic 3DGS framework with hybrid explicit-implicit functions. Our approach contains three key innovations: a spectral-aware Laplacian encoding architecture which merges Hash encoding and Laplacian-based module for flexible frequency motion control, an enhanced Gaussian dynamics attribute that compensates for photometric distortions caused by geometric deformation, and an adaptive Gaussian split strategy guided by KDTree-based primitive control to efficiently query and optimize dynamic areas. Through extensive experiments, our method demonstrates state-of-the-art performance in reconstructing complex dynamic scenes, achieving better reconstruction fidelity. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_04966 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Laplacian Analysis Meets Dynamics Modelling: Gaussian Splatting for 4D Reconstruction Zhou, Yifan Zhao, Beizhen Wu, Pengcheng Wang, Hao Graphics Computer Vision and Pattern Recognition Multimedia While 3D Gaussian Splatting (3DGS) excels in static scene modeling, its extension to dynamic scenes introduces significant challenges. Existing dynamic 3DGS methods suffer from either over-smoothing due to low-rank decomposition or feature collision from high-dimensional grid sampling. This is because of the inherent spectral conflicts between preserving motion details and maintaining deformation consistency at different frequency. To address these challenges, we propose a novel dynamic 3DGS framework with hybrid explicit-implicit functions. Our approach contains three key innovations: a spectral-aware Laplacian encoding architecture which merges Hash encoding and Laplacian-based module for flexible frequency motion control, an enhanced Gaussian dynamics attribute that compensates for photometric distortions caused by geometric deformation, and an adaptive Gaussian split strategy guided by KDTree-based primitive control to efficiently query and optimize dynamic areas. Through extensive experiments, our method demonstrates state-of-the-art performance in reconstructing complex dynamic scenes, achieving better reconstruction fidelity. |
| title | Laplacian Analysis Meets Dynamics Modelling: Gaussian Splatting for 4D Reconstruction |
| topic | Graphics Computer Vision and Pattern Recognition Multimedia |
| url | https://arxiv.org/abs/2508.04966 |