Saved in:
Bibliographic Details
Main Authors: Wang, Tao, Li, Mengyu, Zeng, Geduo, Meng, Cheng, Zhang, Qiong
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2506.09534
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918147754295296
author Wang, Tao
Li, Mengyu
Zeng, Geduo
Meng, Cheng
Zhang, Qiong
author_facet Wang, Tao
Li, Mengyu
Zeng, Geduo
Meng, Cheng
Zhang, Qiong
contents 3D Gaussian Splatting (3DGS) has emerged as a powerful technique for radiance field rendering, but it typically requires millions of redundant Gaussian primitives, overwhelming memory and rendering budgets. Existing compaction approaches address this by pruning Gaussians based on heuristic importance scores, without global fidelity guarantee. To bridge this gap, we propose a novel optimal transport perspective that casts 3DGS compaction as global Gaussian mixture reduction. Specifically, we first minimize the composite transport divergence over a KD-tree partition to produce a compact geometric representation, and then decouple appearance from geometry by fine-tuning color and opacity attributes with far fewer Gaussian primitives. Experiments on benchmark datasets show that our method (i) yields negligible loss in rendering quality (PSNR, SSIM, LPIPS) compared to vanilla 3DGS with only 10% Gaussians; and (ii) consistently outperforms state-of-the-art 3DGS compaction techniques. Notably, our method is applicable to any stage of vanilla or accelerated 3DGS pipelines, providing an efficient and agnostic pathway to lightweight neural rendering. The code is publicly available at https://github.com/DrunkenPoet/GHAP
format Preprint
id arxiv_https___arxiv_org_abs_2506_09534
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Gaussian Herding across Pens: An Optimal Transport Perspective on Global Gaussian Reduction for 3DGS
Wang, Tao
Li, Mengyu
Zeng, Geduo
Meng, Cheng
Zhang, Qiong
Computer Vision and Pattern Recognition
I.4.5
3D Gaussian Splatting (3DGS) has emerged as a powerful technique for radiance field rendering, but it typically requires millions of redundant Gaussian primitives, overwhelming memory and rendering budgets. Existing compaction approaches address this by pruning Gaussians based on heuristic importance scores, without global fidelity guarantee. To bridge this gap, we propose a novel optimal transport perspective that casts 3DGS compaction as global Gaussian mixture reduction. Specifically, we first minimize the composite transport divergence over a KD-tree partition to produce a compact geometric representation, and then decouple appearance from geometry by fine-tuning color and opacity attributes with far fewer Gaussian primitives. Experiments on benchmark datasets show that our method (i) yields negligible loss in rendering quality (PSNR, SSIM, LPIPS) compared to vanilla 3DGS with only 10% Gaussians; and (ii) consistently outperforms state-of-the-art 3DGS compaction techniques. Notably, our method is applicable to any stage of vanilla or accelerated 3DGS pipelines, providing an efficient and agnostic pathway to lightweight neural rendering. The code is publicly available at https://github.com/DrunkenPoet/GHAP
title Gaussian Herding across Pens: An Optimal Transport Perspective on Global Gaussian Reduction for 3DGS
topic Computer Vision and Pattern Recognition
I.4.5
url https://arxiv.org/abs/2506.09534