Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2509.21702 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914057404022784 |
|---|---|
| author | Lin, Weikai Kondguli, Sushant Marshall, Carl Zhu, Yuhao |
| author_facet | Lin, Weikai Kondguli, Sushant Marshall, Carl Zhu, Yuhao |
| contents | 3D Gaussian Splatting (3DGS) combines classic image-based rendering, pointbased graphics, and modern differentiable techniques, and offers an interesting alternative to traditional physically-based rendering. 3DGS-family models are far from efficient for power-constrained Extended Reality (XR) devices, which need to operate at a Watt-level. This paper introduces PowerGS, the first framework to jointly minimize the rendering and display power in 3DGS under a quality constraint. We present a general problem formulation and show that solving the problem amounts to 1) identifying the iso-quality curve(s) in the landscape subtended by the display and rendering power and 2) identifying the power-minimal point on a given curve, which has a closed-form solution given a proper parameterization of the curves. PowerGS also readily supports foveated rendering for further power savings. Extensive experiments and user studies show that PowerGS achieves up to 86% total power reduction compared to state-of-the-art 3DGS models, with minimal loss in both subjective and objective quality. Code is available at https://github.com/horizon-research/PowerGS. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_21702 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | PowerGS: Display-Rendering Power Co-Optimization for Neural Rendering in Power-Constrained XR Systems Lin, Weikai Kondguli, Sushant Marshall, Carl Zhu, Yuhao Graphics I.3; I.4 3D Gaussian Splatting (3DGS) combines classic image-based rendering, pointbased graphics, and modern differentiable techniques, and offers an interesting alternative to traditional physically-based rendering. 3DGS-family models are far from efficient for power-constrained Extended Reality (XR) devices, which need to operate at a Watt-level. This paper introduces PowerGS, the first framework to jointly minimize the rendering and display power in 3DGS under a quality constraint. We present a general problem formulation and show that solving the problem amounts to 1) identifying the iso-quality curve(s) in the landscape subtended by the display and rendering power and 2) identifying the power-minimal point on a given curve, which has a closed-form solution given a proper parameterization of the curves. PowerGS also readily supports foveated rendering for further power savings. Extensive experiments and user studies show that PowerGS achieves up to 86% total power reduction compared to state-of-the-art 3DGS models, with minimal loss in both subjective and objective quality. Code is available at https://github.com/horizon-research/PowerGS. |
| title | PowerGS: Display-Rendering Power Co-Optimization for Neural Rendering in Power-Constrained XR Systems |
| topic | Graphics I.3; I.4 |
| url | https://arxiv.org/abs/2509.21702 |