A Novel 3D-Unet Deep Learning Framework Based on High-Dimensional Bilateral Grid for Edge Consistent Single Image Depth Estimation

Sharma, Mansi; Sharma, Abheesht; Tushar, Kadvekar Rohit; Panneer, Avinash

doi:10.1109/ic3d51119.2020.9376327

Cited by 7 publications

(4 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Refs. [ 31 , 41 , 42 , 43 , 44 , 45 ] proposed wavelet transform to extract sharp edge and strong object boundaries for image dehazing, enhancing the low–light image, reducing artifacts, image segmentation, and depth map estimation. Here, they replace the down–sampling layer with a DWT and the up–sampling layer with an IWT.…”

Section: Nested Dwt Net Architecturementioning

confidence: 99%

Nested DWT–Based CNN Architecture for Monocular Depth Estimation

Paul

Mishra

Marimuthu

2023

Sensors

View full text Add to dashboard Cite

Applications such as medical diagnosis, navigation, robotics, etc., require 3D images. Recently, deep learning networks have been extensively applied to estimate depth. Depth prediction from 2D images poses a problem that is both ill–posed and non–linear. Such networks are computationally and time–wise expensive as they have dense configurations. Further, the network performance depends on the trained model configuration, the loss functions used, and the dataset applied for training. We propose a moderately dense encoder–decoder network based on discrete wavelet decomposition and trainable coefficients (LL, LH, HL, HH). Our Nested Wavelet–Net (NDWTN) preserves the high–frequency information that is otherwise lost during the downsampling process in the encoder. Furthermore, we study the effect of activation functions, batch normalization, convolution layers, skip, etc., in our models. The network is trained with NYU datasets. Our network trains faster with good results.

show abstract

Section: Nested Dwt Net Architecturementioning

confidence: 99%

Nested DWT–Based CNN Architecture for Monocular Depth Estimation

Paul

Mishra

Marimuthu

2023

Sensors

View full text Add to dashboard Cite

show abstract

“…We use standard error metrics for quantitative analysis: Absolute relative error (absrel), Squared relative error (sqrel), Root mean square error (RMSE), Average log error (log 10 ), threshold accuracy (σ i ) and perception-based Structural Similarity Index Metric (SSIM) [35] [39]. Given a predicted depth image and its corresponding ground truth, the different error metrics are calculated as follows:…”

Section: Comparative Analysismentioning

confidence: 99%

MEStereo-Du2CNN: A Novel Dual Channel CNN for Learning Robust Depth Estimates from Multi-exposure Stereo Images for HDR 3D Applications

Choudhary¹,

Sharma²,

V³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

Display technologies have evolved over the years. It is critical to develop practical HDR capturing, processing, and display solutions to bring 3D technologies to the next level. Depth estimation of multi-exposure stereo image sequences is an essential task in the development of cost-effective 3D HDR video content. In this paper, we develop a novel deep architecture for multi-exposure stereo depth estimation. The proposed architecture has two novel components. First, the stereo matching technique used in traditional stereo depth estimation is revamped. For the stereo depth estimation component of our architecture, a mono-to-stereo transfer learning approach is deployed. The proposed formulation circumvents the cost volume construction requirement, which is replaced by a ResNet based dual-encoder single-decoder CNN with different weights for feature fusion. EfficientNet based blocks are used to learn the disparity. Secondly, we combine disparity maps obtained from the stereo images at different exposure levels using a robust disparity feature fusion approach. The disparity maps obtained at different exposures are merged using weight maps calculated for different quality measures. The final predicted disparity map obtained is more robust and retains best features that preserve the depth discontinuities. The proposed CNN offers flexibility to train using standard dynamic range stereo data or with multi-exposure low dynamic range stereo sequences. In terms of performance, the proposed model surpasses state-of-the-art monocular and stereo depth estimation methods, both quantitatively and qualitatively, on challenging Scene flow and differently exposed Middlebury stereo datasets. The architecture performs exceedingly well on complex natural scenes, demonstrating its usefulness for diverse 3D HDR applications.

show abstract

“…Sharma et al. [17] proposed a novel Bilateral Grid based 3D convolutional neural network, which pays more attention to edges and details. In this paper, we propose a novel monocular image depth estimation algorithm.…”

Section: Introductionmentioning

confidence: 99%

“…Hu et al [16] proposed using multi-scale feature fusion module to obtain higher spatial resolution depth map. Sharma et al [17] proposed a novel Bilateral Grid based 3D convolutional neural network, which pays more attention to edges and details. In this paper, we propose a novel monocular image depth estimation algorithm.…”

Section: Introductionmentioning

confidence: 99%

An unsupervised monocular image depth prediction algorithm using Fourier domain analysis

Chen

Tang

2022

IET Signal Processing

View full text Add to dashboard Cite

Aiming at the problems of high cost and low accuracy of scene details during the depth map generation in 3D reconstruction, we propose an unsupervised monocular image depth prediction algorithm based on Fourier domain analysis. Generally speaking, smallscale images can better display depth details, while large-scale images can more reliably display the depth distribution value of the entire image. In order to take advantage of these complementary properties, we crop the input image with different cropped image ratios to generate multiple disparity map candidates, and then use Fourier frequency domain analysis algorithms to fuse disparity mapping candidates into left and right disparity maps. At the same time, we propose a loss function based on MSSIM to compensate the difference between left and right views and realize unsupervised monocular image depth prediction model training. Experimental results show that our method has good performance on the KITTI dataset.

show abstract

A Novel 3D-Unet Deep Learning Framework Based on High-Dimensional Bilateral Grid for Edge Consistent Single Image Depth Estimation

Cited by 7 publications

References 38 publications

Nested DWT–Based CNN Architecture for Monocular Depth Estimation

Nested DWT–Based CNN Architecture for Monocular Depth Estimation

MEStereo-Du2CNN: A Novel Dual Channel CNN for Learning Robust Depth Estimates from Multi-exposure Stereo Images for HDR 3D Applications

An unsupervised monocular image depth prediction algorithm using Fourier domain analysis

Contact Info

Product

Resources

About