Does 3D Gaussian Splatting Need Accurate Volumetric Rendering?

Since its introduction, 3D Gaussian Splatting (3DGS) has become an important reference method for learning 3D representations of a captured scene, allowing real‐time novel‐view synthesis with high visual quality and fast training times. Neural Radiance Fields (NeRFs), which preceded 3DGS, are based...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Computer graphics forum Jg. 44; H. 2
Hauptverfasser: Celarek, A., Kopanas, G., Drettakis, G., Wimmer, M., Kerbl, B.
Format: Journal Article
Sprache:Englisch
Veröffentlicht: Oxford Blackwell Publishing Ltd 01.05.2025
Wiley
Schlagworte:
Approximation
CCS Concepts
Computer Science
Computing methodologies → Image‐based rendering
Rasterization
Ray tracing
Rendering
Volumetric models
Ray tracing
CCS Concepts Computing methodologies → Image-based rendering Volumetric models Rasterization Ray tracing
Gaussians 3D Gaussian Splatting CCS Concepts
Volumetric models
Computing methodologies → Image-based rendering
Rasterization
ISSN:0167-7055, 1467-8659
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:Since its introduction, 3D Gaussian Splatting (3DGS) has become an important reference method for learning 3D representations of a captured scene, allowing real‐time novel‐view synthesis with high visual quality and fast training times. Neural Radiance Fields (NeRFs), which preceded 3DGS, are based on a principled ray‐marching approach for volumetric rendering. In contrast, while sharing a similar image formation model with NeRF, 3DGS uses a hybrid rendering solution that builds on the strengths of volume rendering and primitive rasterization. A crucial benefit of 3DGS is its performance, achieved through a set of approximations, in many cases with respect to volumetric rendering theory. A naturally arising question is whether replacing these approximations with more principled volumetric rendering solutions can improve the quality of 3DGS. In this paper, we present an in‐depth analysis of the various approximations and assumptions used by the original 3DGS solution. We demonstrate that, while more accurate volumetric rendering can help for low numbers of primitives, the power of efficient optimization and the large number of Gaussians allows 3DGS to outperform volumetric rendering despite its approximations.
Bibliographie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:0167-7055
1467-8659
DOI:10.1111/cgf.70032