StableGS: A Floater-Free Framework for 3D Gaussian Splatting

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Wang, Luchao, Ren, Qian, Liao, Kaimin, Wang, Hua, Chen, Zhi, Tang, Yaohua
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866911089612029952
author Wang, Luchao
Ren, Qian
Liao, Kaimin
Wang, Hua
Chen, Zhi
Tang, Yaohua
author_facet Wang, Luchao
Ren, Qian
Liao, Kaimin
Wang, Hua
Chen, Zhi
Tang, Yaohua
contents 3D Gaussian Splatting (3DGS) reconstructions are plagued by stubborn ``floater" artifacts that degrade their geometric and visual fidelity. We are the first to reveal the root cause: a fundamental conflict in the 3DGS optimization process where the opacity gradients of floaters vanish when their blended color reaches a pseudo-equilibrium of canceling errors against the background, trapping them in a spurious local minimum. To resolve this, we propose StableGS, a novel framework that decouples geometric regularization from final appearance rendering. Its core is a Dual Opacity architecture that creates two separate rendering paths: a ``Geometric Regularization Path" to bear strong depth-based constraints for structural correctness, and an ``Appearance Refinement Path" to generate high-fidelity details upon this stable foundation. We complement this with a synergistic set of geometric constraints: a self-supervised depth consistency loss and an external geometric prior enabled by our efficient global scale optimization algorithm. Experiments on multiple benchmarks show StableGS not only eliminates floaters but also resolves the common blur-artifact trade-off, achieving state-of-the-art geometric accuracy and visual quality.
format Preprint
id arxiv_https___arxiv_org_abs_2503_18458
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle StableGS: A Floater-Free Framework for 3D Gaussian Splatting
Wang, Luchao
Ren, Qian
Liao, Kaimin
Wang, Hua
Chen, Zhi
Tang, Yaohua
Computer Vision and Pattern Recognition
Computation and Language
3D Gaussian Splatting (3DGS) reconstructions are plagued by stubborn ``floater" artifacts that degrade their geometric and visual fidelity. We are the first to reveal the root cause: a fundamental conflict in the 3DGS optimization process where the opacity gradients of floaters vanish when their blended color reaches a pseudo-equilibrium of canceling errors against the background, trapping them in a spurious local minimum. To resolve this, we propose StableGS, a novel framework that decouples geometric regularization from final appearance rendering. Its core is a Dual Opacity architecture that creates two separate rendering paths: a ``Geometric Regularization Path" to bear strong depth-based constraints for structural correctness, and an ``Appearance Refinement Path" to generate high-fidelity details upon this stable foundation. We complement this with a synergistic set of geometric constraints: a self-supervised depth consistency loss and an external geometric prior enabled by our efficient global scale optimization algorithm. Experiments on multiple benchmarks show StableGS not only eliminates floaters but also resolves the common blur-artifact trade-off, achieving state-of-the-art geometric accuracy and visual quality.
title StableGS: A Floater-Free Framework for 3D Gaussian Splatting
topic Computer Vision and Pattern Recognition
Computation and Language
url https://arxiv.org/abs/2503.18458