End-to-End Rate-Distortion Optimized 3D Gaussian Representation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Wang, Henan, Zhu, Hanxin, He, Tianyu, Feng, Runsen, Deng, Jiajun, Bian, Jiang, Chen, Zhibo
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913555594346496
author Wang, Henan
Zhu, Hanxin
He, Tianyu
Feng, Runsen
Deng, Jiajun
Bian, Jiang
Chen, Zhibo
author_facet Wang, Henan
Zhu, Hanxin
He, Tianyu
Feng, Runsen
Deng, Jiajun
Bian, Jiang
Chen, Zhibo
contents 3D Gaussian Splatting (3DGS) has become an emerging technique with remarkable potential in 3D representation and image rendering. However, the substantial storage overhead of 3DGS significantly impedes its practical applications. In this work, we formulate the compact 3D Gaussian learning as an end-to-end Rate-Distortion Optimization (RDO) problem and propose RDO-Gaussian that can achieve flexible and continuous rate control. RDO-Gaussian addresses two main issues that exist in current schemes: 1) Different from prior endeavors that minimize the rate under the fixed distortion, we introduce dynamic pruning and entropy-constrained vector quantization (ECVQ) that optimize the rate and distortion at the same time. 2) Previous works treat the colors of each Gaussian equally, while we model the colors of different regions and materials with learnable numbers of parameters. We verify our method on both real and synthetic scenes, showcasing that RDO-Gaussian greatly reduces the size of 3D Gaussian over 40x, and surpasses existing methods in rate-distortion performance.
format Preprint
id arxiv_https___arxiv_org_abs_2406_01597
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle End-to-End Rate-Distortion Optimized 3D Gaussian Representation
Wang, Henan
Zhu, Hanxin
He, Tianyu
Feng, Runsen
Deng, Jiajun
Bian, Jiang
Chen, Zhibo
Computer Vision and Pattern Recognition
Graphics
3D Gaussian Splatting (3DGS) has become an emerging technique with remarkable potential in 3D representation and image rendering. However, the substantial storage overhead of 3DGS significantly impedes its practical applications. In this work, we formulate the compact 3D Gaussian learning as an end-to-end Rate-Distortion Optimization (RDO) problem and propose RDO-Gaussian that can achieve flexible and continuous rate control. RDO-Gaussian addresses two main issues that exist in current schemes: 1) Different from prior endeavors that minimize the rate under the fixed distortion, we introduce dynamic pruning and entropy-constrained vector quantization (ECVQ) that optimize the rate and distortion at the same time. 2) Previous works treat the colors of each Gaussian equally, while we model the colors of different regions and materials with learnable numbers of parameters. We verify our method on both real and synthetic scenes, showcasing that RDO-Gaussian greatly reduces the size of 3D Gaussian over 40x, and surpasses existing methods in rate-distortion performance.
title End-to-End Rate-Distortion Optimized 3D Gaussian Representation
topic Computer Vision and Pattern Recognition
Graphics
url https://arxiv.org/abs/2406.01597