一句话：MetaSapiens 结合效率感知剪枝、注视点渲染与专用加速器，首次在移动端实现保持人眼视觉质量的实时点基神经渲染。
点基神经渲染（PBNR）是面向 AR/VR 与数字孪生的新兴渲染技术，但在移动设备上实现实时且保持视觉质量十分困难。本文提出 MetaSapiens，一个移动端实时 PBNR 系统，包含三项技术：一是效率感知剪枝，在优化渲染速度的同时控制质量损失；二是面向 PBNR 的注视点渲染（FR）方法，利用人眼外周视觉敏锐度较低的特点放宽外围区域渲染质量以提升速度；三是针对 FR 的加速器设计，解决基于 FR 的 PBNR 中负载不均衡问题。评估表明，该系统相较现有 PBNR 模型取得数量级加速，且用户研究确认主观视觉质量未受损害。代码与演示已公开。
Point-Based Neural Rendering (PBNR) is emerging as a promising class of rendering techniques, which are permeating all aspects of society, driven by a growing demand for real-time, photorealistic rendering in AR/VR and digital twins. Achieving real-time PBNR on mobile devices is challenging. This paper proposes MetaSapiens, a PBNR system that for the first time delivers real-time neural rendering on mobile devices while maintaining human visual quality. MetaSapiens combines three techniques. First, we present an efficiency-aware pruning technique to optimize rendering speed. Second, we introduce a Foveated Rendering (FR) method for PBNR, leveraging humans' low visual acuity in peripheral regions to relax rendering quality and improve rendering speed. Finally, we propose an accelerator design for FR, addressing the load imbalance issue in (FR-based) PBNR. Our evaluation shows that our system achieves an order of magnitude speedup over existing PBNR models without sacrificing subjective visual quality, as confirmed by a user study. The code and demo are available at: https://horizon-lab.org/metasapiens/.
DOI 原文 · arXiv · PDF（开放获取） · DBLP
@inproceedings{Lin0025,
title = {<scp>MetaSapiens:</scp>
Real-Time Neural Rendering with Efficiency-Aware Pruning and Accelerated Foveated Rendering},
author = {Weikai Lin and Yu Feng and Yuhao Zhu},
booktitle = {ASPLOS},
year = {2025},
doi = {10.1145/3669940.3707227}
}