Skip to main navigation Skip to search Skip to main content

HAC: Hash-Grid Assisted Context for 3D Gaussian Splatting Compression

Research output: Chapter in Book/Report/Conference proceeding › Conference Paper › Research › peer-review

Abstract

3D Gaussian Splatting (3DGS) has emerged as a promising framework for novel view synthesis, boasting rapid rendering speed with high fidelity. However, the substantial Gaussians and their associated attributes necessitate effective compression techniques. Nevertheless, the sparse and unorganized nature of the point cloud of Gaussians (or anchors in our paper) presents challenges for compression. To address this, we make use of the relations between the unorganized anchors and the structured hash grid, leveraging their mutual information for context modeling, and propose a Hash-grid Assisted Context (HAC) framework for highly compact 3DGS representation. Our approach introduces a binary hash grid to establish continuous spatial consistencies, allowing us to unveil the inherent spatial relations of anchors through a carefully designed context model. To facilitate entropy coding, we utilize Gaussian distributions to accurately estimate the probability of each quantized attribute, where an adaptive quantization module is proposed to enable high-precision quantization of these attributes for improved fidelity restoration. Additionally, we incorporate an adaptive masking strategy to eliminate invalid Gaussians and anchors. Importantly, our work is the pioneer to explore context-based compression for 3DGS representation, resulting in a remarkable size reduction of over 75× compared to vanilla 3DGS, while simultaneously improving fidelity, and achieving over 11× size reduction over SoTA 3DGS compression approach Scaffold-GS. Our code is available here.

Original languageEnglish
Title of host publicationComputer Vision – ECCV 2024 - 18th European Conference Milan, Italy, September 29–October 4, 2024 Proceedings, Part VII
EditorsAleš Leonardis, Elisa Ricci, Stefan Roth, Olga Russakovsky, Torsten Sattler, Gül Varol
Place of PublicationCham Switzerland
PublisherSpringer
Pages422-438
Number of pages17
ISBN (Electronic)9783031726675
ISBN (Print)9783031726668
DOIs
Publication statusPublished - 2025
EventEuropean Conference on Computer Vision 2024 - Milan, Italy
Duration: 29 Sept 2024 → 4 Oct 2024
Conference number: 18th
https://eccv2024.ecva.net/Conferences/2024/Dates
http://chrome-extension://efaidnbmnnnibpcajpcglclefindmkaj/https://media.eventhosts.cc/Conferences/ECCV2024/ConferenceProgram.pdf (Proceedings)

Publication series

NameLecture Notes in Computer Science
PublisherSpringe
Volume15065
ISSN (Print)0302-9743
ISSN (Electronic)1611-3349

Conference

ConferenceEuropean Conference on Computer Vision 2024
Abbreviated titleECCV 2024
Country/TerritoryItaly
CityMilan
Period29/09/24 → 4/10/24
Internet address

Keywords

  • 3D Gaussian Splatting
  • Compression
  • Context Models

Cite this