NeuGPU: A 18.5mJ/Iter Neural-Graphics Processing Unit for Instant-Modeling and Real-Time Rendering with SegmentedHashing Architecture

📋 论文概要

本文提出NeuGPU，一种支持即时建模和实时渲染的神经图形处理单元，通过分段哈希技术解决了传统NeRF训练耗时过长的问题，实现了高效3D建模和渲染，能量效率达18.5mJ/Iter。

💡 主要创新点

• 提出NeuGPU架构，首次实现即时建模与实时渲染的联合硬件加速，无需手动设计或高成本3D扫描。
• 采用分段哈希（Segmented Hashing）方法优化内存访问和计算，显著降低训练与推理延迟。
• 在移动设备目标场景下实现高能效，单次迭代能耗仅18.5mJ，支撑instant modeling应用。

🏷 关键词

📄 原文摘要

Cambridge, MA 1 2 With the rise of the metaverse, there’s a growing demand for 3D modeling and rendering technologies that can bring real-world objects/scenes into the augmented/virtual world on mobile devices. Recently, 3D modeling and rendering using neural radiance field (NeRF) [1] are emerging as NeRF uses only 2D images to train a DNN and create a realistic 3D model without a user’s manual design or high-cost 3D scanner. Previous NeRF hardware [2] supported only high-fps 3D rendering of unseen views without the capability of instant modeling, because the vanilla NeRF model [1] takes 1-2 days to complete 3D modeling on a single NVIDIA V100 GPU. A recent NeRF model [3] enables relatively quick modeling by adopting hash embedding as shown in Fig. 20.7.1. However,

👥 作者与机构

Junha Ryu1, Hankyul Kwon1, Wonhoon Park1, Zhiyong Li1, Beomseok Kwon1,

Donghyeon Han2, Dongseok Im1, Sangyeob Kim1, Hyungnam Joo1, Hoi-Jun Yoo1 Korea Advanced Institute of Science and Technology, Daejeon, Korea Massachusetts Institute of Technology