We propose a new hologram representation based on structured complex-valued 2D Gaussian primitives, which replaces per-pixel information storage and reduces the parameter search space by up to 10:1. To enable end-to-end training, we develop a differentiable rasterizer for our representation, integrated with a GPU-optimized light propagation kernel in free space. Our extensive experiments show that our method achieves up to 2.5x lower VRAM usage and 50% faster optimization while producing higher-fidelity reconstructions than existing methods. We further introduce a conversion procedure that adapts our representation to practical hologram formats, including smooth and random phase-only holograms. Our experiments show that this procedure can effectively suppress noise artifacts observed in previous methods. By reducing the hologram parameter search space, our representation enables a more scalable hologram estimation in the next-generation computer-generated holography systems.

翻译：我们提出了一种基于结构化复值二维高斯基元的新全息图表示方法，该方法替代了逐像素信息存储，并将参数搜索空间减少了高达10:1。为实现端到端训练，我们为该表示开发了一个可微光栅化器，并与自由空间中GPU优化的光传播内核集成。我们的大量实验表明，与现有方法相比，我们的方法实现了高达2.5倍更低的显存使用量和50%更快的优化速度，同时生成更高保真度的重建结果。我们进一步引入了一种转换流程，使我们的表示能够适配实际全息图格式，包括平滑和随机纯相位全息图。实验表明，该流程能有效抑制先前方法中观察到的噪声伪影。通过减少全息图参数搜索空间，我们的表示为下一代计算机生成全息系统实现了更具可扩展性的全息图估计。