Guardado en:
| Autores principales: | , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | https://arxiv.org/abs/2510.22718 |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866912858815594496 |
|---|---|
| author | Wan, Yujie Liu, Chenxuan Wang, Shuai Zhang, Tong Yu, James Jianqiao Ye, Kejiang Niyato, Dusit Xu, Chengzhong |
| author_facet | Wan, Yujie Liu, Chenxuan Wang, Shuai Zhang, Tong Yu, James Jianqiao Ye, Kejiang Niyato, Dusit Xu, Chengzhong |
| contents | Gaussian splatting (GS) struggles with degraded rendering quality on low-cost devices. To address this issue, we present edge collaborative GS (ECO-GS), where each user can switch between a local small GS model to guarantee timeliness and a remote large GS model to guarantee fidelity. However, deciding how to engage the large GS model is nontrivial, due to the interdependency between rendering requirements and resource conditions. To this end, we propose integrated rendering and communication (IRAC), which jointly optimizes collaboration status (i.e., deciding whether to engage large GS) and edge power allocation (i.e., enabling remote rendering) under communication constraints across different users by minimizing a newly-derived GS switching function. Despite the nonconvexity of the problem, we propose an efficient penalty majorization minimization (PMM) algorithm to obtain the critical point solution. Furthermore, we develop an imitation learning optimization (ILO) algorithm, which reduces the computational time by over 100x compared to PMM. Experiments demonstrate the superiority of PMM and the real-time execution capability of ILO. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_22718 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Edge Collaborative Gaussian Splatting with Integrated Rendering and Communication Wan, Yujie Liu, Chenxuan Wang, Shuai Zhang, Tong Yu, James Jianqiao Ye, Kejiang Niyato, Dusit Xu, Chengzhong Information Theory Computer Vision and Pattern Recognition Gaussian splatting (GS) struggles with degraded rendering quality on low-cost devices. To address this issue, we present edge collaborative GS (ECO-GS), where each user can switch between a local small GS model to guarantee timeliness and a remote large GS model to guarantee fidelity. However, deciding how to engage the large GS model is nontrivial, due to the interdependency between rendering requirements and resource conditions. To this end, we propose integrated rendering and communication (IRAC), which jointly optimizes collaboration status (i.e., deciding whether to engage large GS) and edge power allocation (i.e., enabling remote rendering) under communication constraints across different users by minimizing a newly-derived GS switching function. Despite the nonconvexity of the problem, we propose an efficient penalty majorization minimization (PMM) algorithm to obtain the critical point solution. Furthermore, we develop an imitation learning optimization (ILO) algorithm, which reduces the computational time by over 100x compared to PMM. Experiments demonstrate the superiority of PMM and the real-time execution capability of ILO. |
| title | Edge Collaborative Gaussian Splatting with Integrated Rendering and Communication |
| topic | Information Theory Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2510.22718 |