gokhankocmarli/inline-digital-holography-v2

该数据集提供了在模拟环境中表示内联全息成像的合成图像三元组。每个数据样本包括：1. 物体域场（ground truth）；2. 其对应的前向传播全息图（传感器平面的内联全息图案，强度）；3. 数值重建图像（通过角谱方法）。数据集旨在促进计算成像、全息重建、相位检索和基于机器学习的全息图分析研究。数据集由Gökhan Koçmarlı创建，使用Hologen工具包生成，包含12000个样本，总大小为53GB。数据集还包含8种噪声配置类型，每种配置有1500个样本。

This dataset provides synthetic image triplets representing inline holographical imaging in a simulated environment. Each data sample consists of: 1. An object-domain field (ground truth), 2. Its corresponding forward-propagated hologram (the inline holographic pattern at the sensor plane, intensity), 3. The numerically reconstructed image (via angular spectrum method). The dataset is intended to facilitate research in computational imaging, holographic reconstruction, phase retrieval, and machine learning-based hologram analysis. It is created by Gökhan Koçmarlı using the HoloGen Toolkit, containing 12000 samples with a total size of 53GB. The dataset also includes 8 noise configuration types, each with 1500 samples.