Deep Learning-based High-precision Depth Map Estimation from Missing Viewpoints for 360 Degree Digital Holography

TL;DR

This paper introduces HDD Net, a convolutional neural network that accurately estimates depth maps from missing viewpoints to enhance 3D holographic content creation, improving phase extraction and hologram synthesis.

Contribution

The paper presents a novel deep learning model, HDD Net, specifically designed for high-precision depth map estimation from incomplete multi-view data for holography applications.

Findings

HDD Net achieves high PSNR, ACC, and low RMSE in depth estimation.

Depth maps from HDD Net improve hologram quality compared to ground truth-based methods.

Reconstructed holographic scenes demonstrate the effectiveness of the estimated depth maps.

Abstract

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.