Computer-generated holography (CGH) is a promising technology for augmented reality displays, such as head-mounted or head-up displays. However, its high computational demand makes it impractical for implementation. Recent efforts to integrate neural networks into CGH have successfully accelerated computing speed, demonstrating the potential to overcome the trade-off between computational cost and image quality. Nevertheless, deploying neural network-based CGH algorithms on computationally limited embedded systems requires more efficient models with lower computational cost, memory footprint, and power consumption. In this study, we developed a lightweight model for complex hologram generation by introducing neural network quantization. Specifically, we built a model based on tensor holography and quantized it from 32-bit floating-point precision (FP32) to 8-bit integer precision (INT8). Our performance evaluation shows that the proposed INT8 model achieves hologram quality comparable to that of the FP32 model while reducing the model size by approximately 70% and increasing the speed fourfold. Additionally, we implemented the INT8 model on a system-on-module to demonstrate its deployability on embedded platforms and high power efficiency.

翻译：计算机生成全息术（CGH）是一种用于增强现实显示（如头戴式或平视显示器）的有前景的技术。然而，其高计算需求使其在实际应用中难以实现。近期将神经网络集成到CGH中的努力已成功提升了计算速度，展现了克服计算成本与图像质量之间权衡的潜力。尽管如此，在计算能力有限的嵌入式系统上部署基于神经网络的CGH算法，需要具有更低计算成本、内存占用和功耗的更高效模型。在本研究中，我们通过引入神经网络量化，开发了一种用于复全息图生成的轻量级模型。具体而言，我们构建了一个基于张量全息术的模型，并将其从32位浮点精度（FP32）量化为8位整数精度（INT8）。我们的性能评估表明，所提出的INT8模型在实现与FP32模型相当的全息图质量的同时，将模型大小减少了约70%，并将速度提高了四倍。此外，我们在一个系统模块上实现了INT8模型，以展示其在嵌入式平台上的可部署性和高能效。