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）是一项用于增强现实显示（如头戴式或抬头显示）的前沿技术。然而，其高计算需求使其在实际应用中面临挑战。近期将神经网络集成到CGH中的研究已成功提升了计算速度，展现了在计算成本与图像质量之间实现平衡的潜力。尽管如此，在计算资源受限的嵌入式系统上部署基于神经网络的CGH算法，需要具备更低计算成本、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技术，开发了一种用于复全息图生成的轻量级模型。具体而言，我们基于张量全息术构建模型，并将其从32位浮点精度（FP32）量化至8位整数精度（INT8）。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%，并将速度提升了四倍。此外，我们在模块化系统上实现了INT8模型，以验证其在嵌入式平台上的可部署性及高能效特性。