# PowerGS: Display-Rendering Power Co-Optimization for Neural Rendering in Power-Constrained XR Systems

arXiv: https://arxiv.org/abs/2509.21702 · HTML: https://mlsanity.com/paper/2509.21702/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 25 Sep 2025.

## Built on by (most cited first, 3 of 3)

- [ControlGS: Conditioning Neural Gaussians for Downstream-Processing-Aware XR Rendering](https://mlsanity.com/paper/2609.32038/) (2026)
- [Multidimensional Observer Model and Perceptual Dimensions of Human Image Quality Assessment](https://mlsanity.com/paper/2609.38487/) (2026)
- [GazeFlow: From Human Gaze Behavior to Generative Egocentric Gaze Prediction](https://mlsanity.com/paper/2609.38519/) (2026)

## Abstract (arXiv)

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.