Lumina: Real-Time Mobile Neural Rendering by Exploiting Computational Redundancy

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Feng, Yu, Lin, Weikai, Cheng, Yuge, Liu, Zihan, Leng, Jingwen, Guo, Minyi, Chen, Chen, Sun, Shixuan, Zhu, Yuhao
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909640922497024
author Feng, Yu
Lin, Weikai
Cheng, Yuge
Liu, Zihan
Leng, Jingwen
Guo, Minyi
Chen, Chen
Sun, Shixuan
Zhu, Yuhao
author_facet Feng, Yu
Lin, Weikai
Cheng, Yuge
Liu, Zihan
Leng, Jingwen
Guo, Minyi
Chen, Chen
Sun, Shixuan
Zhu, Yuhao
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2506_05682
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Lumina: Real-Time Mobile Neural Rendering by Exploiting Computational Redundancy
Feng, Yu
Lin, Weikai
Cheng, Yuge
Liu, Zihan
Leng, Jingwen
Guo, Minyi
Chen, Chen
Sun, Shixuan
Zhu, Yuhao
Hardware Architecture
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.
title Lumina: Real-Time Mobile Neural Rendering by Exploiting Computational Redundancy
topic Hardware Architecture
url https://arxiv.org/abs/2506.05682