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

arXiv: https://arxiv.org/abs/2103.05158 · HTML: https://mlsanity.com/paper/2103.05158/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 30 references that are in the map.
- First posted on arXiv 9 Mar 2021.

## Builds on (most cited first, 10 of 10)

- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Depth Map Prediction from a Single Image using a Multi-Scale Deep Network](https://mlsanity.com/paper/1406.2283/) (2014)
- [Deep Ordinal Regression Network for Monocular Depth Estimation](https://mlsanity.com/paper/1806.02446/) (2018)
- [Learning Depth from Single Monocular Images Using Deep Convolutional Neural Fields](https://mlsanity.com/paper/1502.07411/) (2015)
- [Evaluation of CNN-based Single-Image Depth Estimation Methods](https://mlsanity.com/paper/1805.01328/) (2018)
- [High Quality Monocular Depth Estimation via Transfer Learning](https://mlsanity.com/paper/1812.11941/) (2018)
- [DPSNet: End-to-end Deep Plane Sweep Stereo](https://mlsanity.com/paper/1905.00538/) (2019)
- [MVDepthNet: Real-time Multiview Depth Estimation Neural Network](https://mlsanity.com/paper/1807.08563/) (2018)
- [Fusion of stereo and still monocular depth estimates in a self-supervised learning context](https://mlsanity.com/paper/1803.07512/) (2018)
- [DepthNet Nano: A Highly Compact Self-Normalizing Neural Network for Monocular Depth Estimation](https://mlsanity.com/paper/2004.08008/) (2020)

## Built on by (most cited first, 1 of 1)

- [Central Angle Optimization for 360-degree Holographic 3D Content](https://mlsanity.com/paper/2311.05878/) (2023)

## Abstract (arXiv)

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.