发表机构
University of Cambridge（剑桥大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本文提出一种紧凑可微的夫琅禾费全息投影仪数字孪生模型，原位识别硬件参数，实现全视场全息图案化，并抑制杂散光伪影，适用于无掩模光刻和光镊阵列。
AI 中文摘要
计算机生成全息术能够实现对光场近乎完全的动态控制，但理想化传播模型与物理硬件之间的差异限制了其性能，尤其是在大视场范围内。我们提出了一种紧凑的夫琅禾费全息投影仪可微模型，该模型描述了从纯相位空间光调制器（SLM）到记录傅里叶透镜焦平面的相机的完整传播链。该模型使用物理上可解释的参数来描述SLM、照明、光瞳、相干杂散光和相机。该模型通过噪声探测的全息图-图像对在原位进行识别，无需额外硬件、系统修改或相机在环优化。恢复的数字孪生用于生成覆盖SLM空间带宽限制下整个第一衍射级图案的全息图。这种全视场能力通过测量视场相关光瞳像差，并在$4\pi$相位调制范围内操作以补偿严重的像素间串扰来实现。导致残余零级伪影的杂散光在振幅和相位上被恢复，从而可以研究其物理来源，并在全息图合成过程中抑制其贡献。该工作为夫琅禾费区域工作的全息系统中校准感知场合成建立了框架，适用于无掩模光刻和光镊阵列等应用。
英文摘要
Computer-generated holography allows for nearly complete dynamic control of optical fields, but discrepancies between idealised propagation models and physical hardware limit its performance, particularly across large fields of view. We present a compact differentiable model of a Fraunhofer holographic projector which describes the complete propagation chain, from a phase-only spatial light modulator (SLM) to the camera recording the focal plane of a Fourier lens. It uses physically interpretable parameters for the SLM, illumination, pupil, coherent stray light, and camera. The model is identified in situ from noise-probed hologram-image pairs without additional hardware, system modification, or camera-in-the-loop refinement. The recovered digital twin is used to generate holograms for patterns spanning the entire first diffraction order of the SLM at its spatial-bandwidth limit. This full-field capability is enabled by measuring field-dependent pupil aberrations and compensating severe inter-pixel crosstalk by operating at the $4π$ phase modulation range. The stray light responsible for residual zeroth-order artefacts is recovered in amplitude and phase, allowing its physical origin to be investigated, and its contribution suppressed during hologram synthesis. The work establishes a framework for calibration-aware field synthesis in holographic systems operating in the Fraunhofer regime for applications such as maskless lithography and optical tweezer arrays.
CommentsMain manuscript: 18 pages, 6 figures. Supplementary information: 17 pages, 10 figures, 2 tables
