Skip to main navigation Skip to search Skip to main content

Normal-GS: 3D Gaussian Splatting with Normal-Involved Rendering

Research output: Chapter in Book/Report/Conference proceedingConference PaperResearchpeer-review

Abstract

Rendering and reconstruction are long-standing topics in computer vision and graphics. Achieving both high rendering quality and accurate geometry is a challenge. Recent advancements in 3D Gaussian Splatting (3DGS) have enabled high-fidelity novel view synthesis at real-time speeds. However, the noisy and discrete nature of 3D Gaussian primitives hinders accurate surface estimation. Previous attempts to regularize 3D Gaussian normals often degrade rendering quality due to the fundamental disconnect between normal vectors and the rendering pipeline in 3DGS-based methods. Therefore, we introduce Normal-GS, a novel approach that integrates normal vectors into the 3DGS rendering pipeline. The core idea is to model the interaction between normals and incident lighting using the physically-based rendering equation. Our approach re-parameterizes surface colors as the product of normals and a designed Integrated Directional Illumination Vector (IDIV). To save memory usage and simplify the optimization, we employ an anchor-based 3DGS to implicitly encode locally-shared IDIVs. Additionally, Normal-GS leverages optimized normals and Integrated Directional Encoding (IDE) to accurately model specular effects, enhancing both rendering quality and surface normal precision. Extensive experiments demonstrate that Normal-GS achieves near state-of-the-art visual quality while obtaining accurate surface normals and preserving real-time rendering performance.

Original languageEnglish
Title of host publicationNeurIPS Proceedings - Advances in Neural Information Processing Systems 37 (NeurIPS 2024)
EditorsA. Globerson, L. Mackey, D. Belgrave, A. Fan, U. Paquet, J. Tomczak, C. Zhang
Place of PublicationSan Diego CA USA
PublisherNeural Information Processing Systems (NIPS)
Number of pages24
ISBN (Electronic)9798331314385
Publication statusPublished - 2024
EventAdvances in Neural Information Processing Systems 2024 - Vancouver, Canada
Duration: 10 Dec 202415 Dec 2024
Conference number: 38th
https://neurips.cc/ (Website)
https://openreview.net/group?id=NeurIPS.cc/2024/Conference#tab-accept-oral (Peer Reviews)
https://proceedings.neurips.cc/paper_files/paper/2024 (Proceedings - NeurIPS Proceedings)

Publication series

NameAdvances in Neural Information Processing Systems
PublisherNeural Information Processing Systems (NIPS)
Volume37
ISSN (Print)1049-5258

Conference

ConferenceAdvances in Neural Information Processing Systems 2024
Abbreviated titleNeurIPS 2024
Country/TerritoryCanada
CityVancouver
Period10/12/2415/12/24
Internet address

Cite this