Lumina: Real-Time Mobile Neural Rendering by Exploiting Computational Redundancy
Preprint
Abstract
3D Gaussian Splatting (3DGS) has vastly advanced the pace of neural rendering, but it remains computationally demanding on today's mobile SoCs. To address this challenge, we propose Lumina, a hardware-algorithm co-designed system, which integrates two principal optimizations: a novel algorithm, S^2, and a radiance caching mechanism, RC, to improve the efficiency of neural rendering. S2 algorithm exploits temporal coherence in rendering to reduce the computational overhead, while RC leverages the color integration process of 3DGS to decrease the frequency of intensive rasterization computations. Coupled with these techniques, we propose an accelerator architecture, LuminCore, to further accelerate cache lookup and address the fundamental inefficiencies in Rasterization. We show that Lumina achieves 4.5x speedup and 5.3x energy reduction against a mobile Volta GPU, with a marginal quality loss (< 0.2 dB peak signal-to-noise ratio reduction) across synthetic and real-world datasets.Keywords
All Related Versions
This publication has 18 references indexed in Scilit:
- VR-Pipe: Streamlining Hardware Graphics Pipeline for Volume Rendering2025
- Mini-Splatting: Representing Scenes with a Constrained Number of Gaussians2024
- CityGaussian: Real-Time High-Quality Large-Scale Scene Rendering with Gaussians2024
- Recent advances in 3D Gaussian splattingComputational Visual Media, 2024
- Cicero: Addressing Algorithmic and Architectural Bottlenecks in Neural Rendering by Radiance Warping and Memory Optimizations2024
- Mip-NeRF 360: Unbounded Anti-Aliased Neural Radiance Fields2022
- GANAX: A Unified MIMD-SIMD Acceleration for Generative Adversarial Networks2018
- Euphrates: Algorithm-SoC Co-Design for Low-Power Mobile Continuous Vision2018
- Scaling equations for the accurate prediction of CMOS device performance from 180 nm to 7 nmIntegration, 2017
- The physics of optimal decision making: A formal analysis of models of performance in two-alternative forced-choice tasks.Psychological Review, 2006