基于深度学习的360度数字全息缺失视点高精度深度图估计
Deep Learning-based High-precision Depth Map Estimation from Missing Viewpoints for 360 Degree Digital Holography
摘要：
在本文中，我们提出了一种新的，卷积神经网络模型，以提取高精度的深度图缺失的观点，特别是适用于生成全息3D内容。深度图是计算全息图（CGH）合成所需的相位提取的基本要素。提出的模型称为HDD Net使用MSE作为损失函数以获得更好的深度图估计性能，并在上采样层中使用Relu作为激活函数的双线性插值。我们设计并准备了总共8,192张多视角图像，每张分辨率为640 × 360，用于深度学习研究。该模型通过提取特征、上采样来估计深度图。对于定量评估，我们通过使用PSNR，ACC和RMSE将估计的深度图与地面实况进行比较。我们还比较了CGH模式估计的深度图与地面实况。此外，我们展示了实验结果，以测试通过直接重建全息三维图像场景的CGH估计的深度图的质量。
英文摘要：
In this paper, we propose a novel, convolutional neural network model to extract highly precise depth maps from missing viewpoints, especially well applicable to generate holographic 3D contents. The depth map is an essential element for phase extraction which is required for synthesis of computer-generated hologram (CGH). The proposed model called the HDD Net uses MSE for the better performance of depth map estimation as loss function, and utilizes the bilinear interpolation in up sampling layer with the Relu as activation function. We design and prepare a total of 8,192 multi-view images, each resolution of 640 by 360 for the deep learning study. The proposed model estimates depth maps through extracting features, up sampling. For quantitative assessment, we compare the estimated depth maps with the ground truths by using the PSNR, ACC, and RMSE. We also compare the CGH patterns made from estimated depth maps with ones made from ground truths. Furthermore, we demonstrate the experimental results to test the quality of estimated depth maps through directly reconstructing holographic 3D image scenes from the CGHs.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
