Compressed 3D Gaussian Splatting for Accelerated Novel View Synthesis

Simon Niedermayr, Josef Stumpfegger, Rüdiger Westermann

Publikation: Beitrag in Buch/Bericht/KonferenzbandKonferenzbeitragBegutachtung

12 Zitate (Scopus)

Abstract

Recently, high-fidelity scene reconstruction with an optimized 3D Gaussian splat representation has been introducedfor novel view synthesis from sparse image sets. Making such representations suitable for applications like network streaming and rendering on low-power devices requires significantly reduced memory consumption as well as improved rendering efficiency. We propose a compressed 3D Gaussian splat representation that utilizes sensitivity-aware vector clustering with quantization-aware training to compress directional colors and Gaussian parameters. The learned codebooks have low bitrates and achieve a compression rate of up to 31 × on real-world scenes with only minimal degradation of visual quality. We demonstrate that the compressed splat representation can be efficiently rendered with hardware rasterization on lightweight GPUs at up to 4 × higher framerates than reported via an optimized GPU compute pipeline. Extensive experiments across multiple datasets demonstrate the robustness and rendering speed of the proposed approach.

OriginalspracheEnglisch
TitelProceedings - 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2024
Herausgeber (Verlag)IEEE Computer Society
Seiten10349-10358
Seitenumfang10
ISBN (elektronisch)9798350353006
DOIs
PublikationsstatusVeröffentlicht - 2024
Veranstaltung2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2024 - Seattle, USA/Vereinigte Staaten
Dauer: 16 Juni 202422 Juni 2024

Publikationsreihe

NameProceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
ISSN (Print)1063-6919

Konferenz

Konferenz2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2024
Land/GebietUSA/Vereinigte Staaten
OrtSeattle
Zeitraum16/06/2422/06/24

Fingerprint

Untersuchen Sie die Forschungsthemen von „Compressed 3D Gaussian Splatting for Accelerated Novel View Synthesis“. Zusammen bilden sie einen einzigartigen Fingerprint.

Dieses zitieren