PocketGS: On-Device Training of 3D Gaussian Splatting for High Perceptual Modeling
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _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 |