Year: 2025
Type: conference-paper
Abstract: 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.
Source: Computer Science Research Notes
DOI: 10.24132/csrn.2025-6
Authors: Laboratoire SAMOVAR, Telecom SudParis, Institut Polytechnique de Paris, Mohamed ABDUL GAFOOR, Marius PREDA, Laboratoire SAMOVAR, Telecom SudParis, Institut Polytechnique de Paris, Titus ZAHARIA, Laboratoire SAMOVAR, Telecom SudParis, Institut Polytechnique de Paris
Institution: Télécom SudParis
Language: English
Subfield: Computational Mechanics
Field: Engineering
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W4412764689