Saved in:
Bibliographic Details
Main Authors: Guo, Wenzhi, Fang, Guangchi, Yang, Shu, Wang, Bing
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2601.17354
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917537131790336
author Guo, Wenzhi
Fang, Guangchi
Yang, Shu
Wang, Bing
author_facet Guo, Wenzhi
Fang, Guangchi
Yang, Shu
Wang, Bing
contents While 3D Gaussian Splatting (3DGS) enables real-time rendering, its training demands workstation-level compute and memory, making mobile deployment impractical under minute-scale time budgets and limited peak memory. We present PocketGS, a mobile scene modeling paradigm that enables on-device 3DGS training under these tightly coupled constraints while preserving high-fidelity reconstruction. PocketGS resolves the fundamental tension between training efficiency, memory compactness, and modeling quality through three co-designed operators: $\mathcal{G}$ builds geometry-faithful point-cloud priors; $\mathcal{I}$ injects local surface statistics to seed anisotropic Gaussians, thereby reducing early conditioning gaps; and $\mathcal{T}$ unrolls alpha compositing with cached intermediates and index-mapped gradient scattering for stable mobile backpropagation. Extensive experiments demonstrate that PocketGS outperforms the powerful mainstream workstation 3DGS baseline under mobile budgets, delivering high-quality reconstructions and enabling a fully on-device, practical capture-to-rendering workflow.
format Preprint
id arxiv_https___arxiv_org_abs_2601_17354
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle PocketGS: On-Device Training of 3D Gaussian Splatting for High Perceptual Modeling
Guo, Wenzhi
Fang, Guangchi
Yang, Shu
Wang, Bing
Computer Vision and Pattern Recognition
Graphics
While 3D Gaussian Splatting (3DGS) enables real-time rendering, its training demands workstation-level compute and memory, making mobile deployment impractical under minute-scale time budgets and limited peak memory. We present PocketGS, a mobile scene modeling paradigm that enables on-device 3DGS training under these tightly coupled constraints while preserving high-fidelity reconstruction. PocketGS resolves the fundamental tension between training efficiency, memory compactness, and modeling quality through three co-designed operators: $\mathcal{G}$ builds geometry-faithful point-cloud priors; $\mathcal{I}$ injects local surface statistics to seed anisotropic Gaussians, thereby reducing early conditioning gaps; and $\mathcal{T}$ unrolls alpha compositing with cached intermediates and index-mapped gradient scattering for stable mobile backpropagation. Extensive experiments demonstrate that PocketGS outperforms the powerful mainstream workstation 3DGS baseline under mobile budgets, delivering high-quality reconstructions and enabling a fully on-device, practical capture-to-rendering workflow.
title PocketGS: On-Device Training of 3D Gaussian Splatting for High Perceptual Modeling
topic Computer Vision and Pattern Recognition
Graphics
url https://arxiv.org/abs/2601.17354