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

• URL: http://arxiv.org/abs/2103.05158v1
• Date: Tue, 9 Mar 2021 00:38:23 GMT
• Title: Deep Learning-based High-precision Depth Map Estimation from Missing Viewpoints for 360 Degree Digital Holography
• Authors: Hakdong Kim, Heonyeong Lim, Minkyu Jee, Yurim Lee, Jisoo Jeong, Kyudam Choi, MinSung Yoon, and Cheongwon Kim
• Abstract summary: We propose a novel, convolutional neural network model to extract highly precise depth maps from missing viewpoints. The proposed model called the HDD Net uses MSE for the better performance of depth map estimation as loss function. We demonstrate the experimental results to test the quality of estimated depth maps through directly reconstructing holographic 3D image scenes.
• Score: 2.174116094271494
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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.

Related papers

• A Novel Solution for Drone Photogrammetry with Low-overlap Aerial Images using Monocular Depth Estimation [6.689484367905018]
  Low-overlap aerial imagery poses significant challenges to traditional photogrammetric methods. We propose a novel workflow based on monocular depth estimation to address the limitations of conventional techniques.
  arXiv  Detail & Related papers  (2025-03-06T14:59:38Z)
• DepthSplat: Connecting Gaussian Splatting and Depth [90.06180236292866]
  We present DepthSplat to connect Gaussian splatting and depth estimation. We first contribute a robust multi-view depth model by leveraging pre-trained monocular depth features. We also show that Gaussian splatting can serve as an unsupervised pre-training objective.
  arXiv  Detail & Related papers  (2024-10-17T17:59:58Z)
• Refinement of Monocular Depth Maps via Multi-View Differentiable Rendering [4.717325308876748]
  We present a novel approach to generate view consistent and detailed depth maps from a number of posed images. We leverage advances in monocular depth estimation, which generate topologically complete, but metrically inaccurate depth maps. Our method is able to generate dense, detailed, high-quality depth maps, also in challenging indoor scenarios, and outperforms state-of-the-art depth reconstruction approaches.
  arXiv  Detail & Related papers  (2024-10-04T18:50:28Z)
• Central Angle Optimization for 360-degree Holographic 3D Content [3.072340427031969]
  In this study, we propose a method to find an optimal central angle in deep learning-based depth map estimation. We experimentally demonstrate and discuss the relationship between the central angle and the quality of digital holographic content.
  arXiv  Detail & Related papers  (2023-11-10T05:30:43Z)
• HiMODE: A Hybrid Monocular Omnidirectional Depth Estimation Model [3.5290359800552946]
  HiMODE is a novel monocular omnidirectional depth estimation model based on a CNN+Transformer architecture. We show that HiMODE can achieve state-of-the-art performance for 360deg monocular depth estimation.
  arXiv  Detail & Related papers  (2022-04-11T11:11:43Z)
• 3DVNet: Multi-View Depth Prediction and Volumetric Refinement [68.68537312256144]
  3DVNet is a novel multi-view stereo (MVS) depth-prediction method. Our key idea is the use of a 3D scene-modeling network that iteratively updates a set of coarse depth predictions. We show that our method exceeds state-of-the-art accuracy in both depth prediction and 3D reconstruction metrics.
  arXiv  Detail & Related papers  (2021-12-01T00:52:42Z)
• Weakly-Supervised Monocular Depth Estimationwith Resolution-Mismatched Data [73.9872931307401]
  We propose a novel weakly-supervised framework to train a monocular depth estimation network. The proposed framework is composed of a sharing weight monocular depth estimation network and a depth reconstruction network for distillation. Experimental results demonstrate that our method achieves superior performance than unsupervised and semi-supervised learning based schemes.
  arXiv  Detail & Related papers  (2021-09-23T18:04:12Z)
• VolumeFusion: Deep Depth Fusion for 3D Scene Reconstruction [71.83308989022635]
  In this paper, we advocate that replicating the traditional two stages framework with deep neural networks improves both the interpretability and the accuracy of the results. Our network operates in two steps: 1) the local computation of the local depth maps with a deep MVS technique, and, 2) the depth maps and images' features fusion to build a single TSDF volume. In order to improve the matching performance between images acquired from very different viewpoints, we introduce a rotation-invariant 3D convolution kernel called PosedConv.
  arXiv  Detail & Related papers  (2021-08-19T11:33:58Z)
• CAMERAS: Enhanced Resolution And Sanity preserving Class Activation Mapping for image saliency [61.40511574314069]
  Backpropagation image saliency aims at explaining model predictions by estimating model-centric importance of individual pixels in the input. We propose CAMERAS, a technique to compute high-fidelity backpropagation saliency maps without requiring any external priors.
  arXiv  Detail & Related papers  (2021-06-20T08:20:56Z)
• DGGAN: Depth-image Guided Generative Adversarial Networks for Disentangling RGB and Depth Images in 3D Hand Pose Estimation [33.23818997206978]
  Estimating 3D hand poses from RGB images is essential to a wide range of potential applications, but is challengingowing to substantial ambiguity in the inference of depth in-formation from RGB images. We propose a conditional generative adversarial network (GAN) model,called Depth-image Guided GAN (DGGAN), to generate re-alistic depth maps conditioned on the input RGB image. Experimental results on multiplebenchmark datasets show that the synthesized depth mapsproduced by DGGAN are quite effective in regularizing thepose estimation model.
  arXiv  Detail & Related papers  (2020-12-06T07:23:21Z)
• Attention Aware Cost Volume Pyramid Based Multi-view Stereo Network for 3D Reconstruction [12.728154351588053]
  We present an efficient multi-view stereo (MVS) network for 3D reconstruction from multiview images. We introduce a coarseto-fine depth inference strategy to achieve high resolution depth.
  arXiv  Detail & Related papers  (2020-11-25T13:34:11Z)
• Depth Completion Using a View-constrained Deep Prior [73.21559000917554]
  Recent work has shown that the structure of convolutional neural networks (CNNs) induces a strong prior that favors natural images. This prior, known as a deep image prior (DIP), is an effective regularizer in inverse problems such as image denoising and inpainting. We extend the concept of the DIP to depth images. Given color images and noisy and incomplete target depth maps, we reconstruct a depth map restored by virtue of using the CNN network structure as a prior.
  arXiv  Detail & Related papers  (2020-01-21T21:56:01Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.