HERO:面向NeRF量化的硬件高效强化学习优化框架
HERO: Hardware-Efficient RL-based Optimization Framework for NeRF Quantization
AI总结:
针对NeRF量化未考虑硬件架构且依赖人工探索的问题,提出强化学习框架HERO,集成加速器模拟器实现自动化硬件感知量化,相比CAQ显著提升延迟和成本效率。
摘要:
神经辐射场(Neural Radiance Field, NeRF)已成为一种有前景的三维重建方法,为增强现实(AR)和虚拟现实(VR)应用提供了高质量的结果。尽管已有量化方法和硬件加速器被提出以提升NeRF的计算效率,现有方法仍面临关键限制。当前的量化方法在操作时未考虑硬件架构,导致在涵盖精度、延迟和模型规模的广阔设计空间中产生次优解。此外,现有的NeRF加速器严重依赖人类专家来探索这一设计空间,使得优化过程耗时、低效,且难以发现最优解。为应对这些挑战,我们提出了HERO,一个对NeRF执行硬件感知量化的强化学习框架。我们的框架集成了NeRF加速器模拟器以生成实时硬件反馈,从而实现对硬件约束的完全自动化适应。实验结果表明,与之前最先进的NeRF量化框架CAQ相比,HERO实现了1.31-1.33倍的延迟改善、1.29-1.33倍的成本效率提升,以及更紧凑的模型规模。这些结果验证了我们的框架能够有效导航硬件与算法需求之间的复杂设计空间,为NeRF实现发现更优的量化策略。代码可在https://github.com/ypzhng/HERO获取。
英文摘要:
Neural Radiance Field (NeRF) has emerged as a promising 3D reconstruction method, delivering high-quality results for AR/VR applications. While quantization methods and hardware accelerators have been proposed to enhance NeRF's computational efficiency, existing approaches face crucial limitations. Current quantization methods operate without considering hardware architecture, resulting in sub-optimal solutions within the vast design space encompassing accuracy, latency, and model size. Additionally, existing NeRF accelerators heavily rely on human experts to explore this design space, making the optimization process time-consuming, inefficient, and unlikely to discover optimal solutions. To address these challenges, we introduce HERO, a reinforcement learning framework performing hardware-aware quantization for NeRF. Our framework integrates a NeRF accelerator simulator to generate real-time hardware feedback, enabling fully automated adaptation to hardware constraints. Experimental results demonstrate that HERO achieves 1.31-1.33 $\times$ better latency, 1.29-1.33 $\times$ improved cost efficiency, and a more compact model size compared to CAQ, a previous state-of-the-art NeRF quantization framework. These results validate our framework's capability to effectively navigate the complex design space between hardware and algorithm requirements, discovering superior quantization policies for NeRF implementation. Code is available at https://github.com/ypzhng/HERO.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。