用可变形注意力提升全息图生成质量，突破传统方法局限。
Unfolding Framework with Complex-Valued Deformable Attention for High-Quality Computer-Generated Hologram Generation
- 将梯度下降分解为物理可解释的两模块，增强可调控性。
- 在真实与模拟数据上实现超过35 dB的峰值信噪比。
- 适合需要高精度、长距离全息重建的研究者使用。
基于深度学习的计算全息技术受到广泛关注，但因其非线性与病态特性，仍面临重建精度与稳定性难题。首先，主流端到端网络将重建过程视为黑箱，忽略物理规律，降低可解释性与灵活性；其次，基于卷积神经网络的方法感受野有限，难以捕捉长程依赖与全局上下文；再次，基于角谱法（ASM）的模型受限于有限近场。本文提出深度展开网络（DUN），将梯度下降分解为自适应带宽保持模块（ABPM）与相位域复数去噪器（PCD）两个模块，兼具物理可解释性与灵活性。ABPM支持比ASM方法更远的工作距离；PCD引入复数可变形自注意力机制，有效捕获全局特征，显著提升性能，在真实与模拟数据上均达到当前最优结果，峰值信噪比超35 dB。
原文摘要 · Abstract (English)
Computer-generated holography (CGH) has gained wide attention with deep learning-based algorithms. However, due to its nonlinear and ill-posed nature, challenges remain in achieving accurate and stable reconstruction. Specifically, ($i$) the widely used end-to-end networks treat the reconstruction model as a black box, ignoring underlying physical relationships, which reduces interpretability and flexibility. ($ii$) CNN-based CGH algorithms have limited receptive fields, hindering their ability to capture long-range dependencies and global context. ($iii$) Angular spectrum method (ASM)-based models are constrained to finite near-fields.In this paper, we propose a Deep Unfolding Network (DUN) that decomposes gradient descent into two modules: an adaptive bandwidth-preserving model (ABPM) and a phase-domain complex-valued denoiser (PCD), providing more flexibility. ABPM allows for wider working distances compared to ASM-based methods. At the same time, PCD leverages its complex-valued deformable self-attention module to capture global features and enhance performance, achieving a PSNR over 35 dB. Experiments on simulated and real data show state-of-the-art results.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。