Guardado en:
Detalles Bibliográficos
Autores principales: Gafoor, Mohamed Abdul, Preda, Marius, Zaharia, Titus
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:https://arxiv.org/abs/2508.05187
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866909727263293440
author Gafoor, Mohamed Abdul
Preda, Marius
Zaharia, Titus
author_facet Gafoor, Mohamed Abdul
Preda, Marius
Zaharia, Titus
contents Achieving high-quality novel view synthesis in 3D Gaussian Splatting (3DGS) often depends on effective point primitive management. The underlying Adaptive Density Control (ADC) process addresses this issue by automating densification and pruning. Yet, the vanilla 3DGS densification strategy shows key shortcomings. To address this issue, in this paper we introduce a novel density control method, which exploits the volumes of inertia associated to each Gaussian function to guide the refinement process. Furthermore, we study the effect of both traditional Structure from Motion (SfM) and Deep Image Matching (DIM) methods for point cloud initialization. Extensive experimental evaluations on the Mip-NeRF 360 dataset demonstrate that our approach surpasses 3DGS in reconstruction quality, delivering encouraging performance across diverse scenes.
format Preprint
id arxiv_https___arxiv_org_abs_2508_05187
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Refining Gaussian Splatting: A Volumetric Densification Approach
Gafoor, Mohamed Abdul
Preda, Marius
Zaharia, Titus
Graphics
Artificial Intelligence
Computer Vision and Pattern Recognition
Achieving high-quality novel view synthesis in 3D Gaussian Splatting (3DGS) often depends on effective point primitive management. The underlying Adaptive Density Control (ADC) process addresses this issue by automating densification and pruning. Yet, the vanilla 3DGS densification strategy shows key shortcomings. To address this issue, in this paper we introduce a novel density control method, which exploits the volumes of inertia associated to each Gaussian function to guide the refinement process. Furthermore, we study the effect of both traditional Structure from Motion (SfM) and Deep Image Matching (DIM) methods for point cloud initialization. Extensive experimental evaluations on the Mip-NeRF 360 dataset demonstrate that our approach surpasses 3DGS in reconstruction quality, delivering encouraging performance across diverse scenes.
title Refining Gaussian Splatting: A Volumetric Densification Approach
topic Graphics
Artificial Intelligence
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2508.05187