S2DNet: Depth Estimation From Single Image and Sparse Samples

Hambarde, Praful; Murala, Subrahmanyam

doi:10.1109/tci.2020.2981761

Cited by 49 publications

(11 citation statements)

References 61 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As can be seen, MobileXNet performs much better than Spek et al [44] in both error and accuracy metrics, and it generates the best RMSE result. Regarding REL, δ 1 , δ 2 and δ 3 metrics, MobileXNet also outperforms [1], [14], [26], [27], [42], [43]. In addition, the REL, δ 1 , δ 2 and δ 3 values of Mo-bileXNet are on par with [3]- [6].…”

Section: ) Evaluation Of Network Architecturesmentioning

confidence: 85%

MobileXNet: An Efficient Convolutional Neural Network for Monocular Depth Estimation

Dong¹,

Garratt²,

Anavatti³

et al. 2021

Preprint

View full text Add to dashboard Cite

Depth is a vital piece of information for autonomous vehicles to perceive obstacles. Due to the relatively low price and small size of monocular cameras, depth estimation from a single RGB image has attracted great interest in the research community. In recent years, the application of Deep Neural Networks (DNNs) has significantly boosted the accuracy of monocular depth estimation (MDE). State-of-the-art methods are usually designed on top of complex and extremely deep network architectures, which require more computational resources and cannot run in real-time without using high-end GPUs. Although some researchers tried to accelerate the running speed, the accuracy of depth estimation is degraded because the compressed model does not represent images well. In addition, the inherent characteristic of the feature extractor used by the existing approaches results in severe spatial information loss in the produced feature maps, which also impairs the accuracy of depth estimation on small sized images. In this study, we are motivated to design a novel and efficient Convolutional Neural Network (CNN) that assembles two shallow encoder-decoder style subnetworks in succession to address these problems. In particular, we place our emphasis on the trade-off between the accuracy and speed of MDE. Extensive experiments have been conducted on the NYU depth v2, KITTI, Make3D and Unreal data sets. Compared with the state-of-the-art approaches which have an extremely deep and complex architecture, the proposed network not only achieves comparable performance but also runs at a much faster speed on a single, less powerful GPU.

show abstract

Section: ) Evaluation Of Network Architecturesmentioning

confidence: 85%

MobileXNet: An Efficient Convolutional Neural Network for Monocular Depth Estimation

Dong¹,

Garratt²,

Anavatti³

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…Eigen et al [3] proposed the first monocular depth estimation method based on deep learning, which showed a surprising performance than pre-works [1,2]. Then, a lot of excellent works based on deep learning were proposed such as [4][5][6][7][8][9][10][11][12][13][14]. However, monocular depth estimation methods have still suffered from the boundary blur challenge, especially in indoor scenes which have complex scene structures and many objects.…”

Section: Introductionmentioning

confidence: 99%

Monocular Depth Estimation with Sharp Boundary

Xin¹,

Chang²,

Xu³

et al. 2023

Computer Modeling in Engineering &Amp; Sciences

View full text Add to dashboard Cite

Monocular depth estimation is the basic task in computer vision. Its accuracy has tremendous improvement in the decade with the development of deep learning. However, the blurry boundary in the depth map is a serious problem. Researchers find that the blurry boundary is mainly caused by two factors. First, the low-level features, containing boundary and structure information, may be lost in deep networks during the convolution process. Second, the model ignores the errors introduced by the boundary area due to the few portions of the boundary area in the whole area, during the backpropagation. Focusing on the factors mentioned above. Two countermeasures are proposed to mitigate the boundary blur problem. Firstly, we design a scene understanding module and scale transform module to build a lightweight fuse feature pyramid, which can deal with low-level feature loss effectively. Secondly, we propose a boundary-aware depth loss function to pay attention to the effects of the boundary's depth value. Extensive experiments show that our method can predict the depth maps with clearer boundaries, and the performance of the depth accuracy based on NYU-Depth V2, SUN RGB-D, and iBims-1 are competitive.

show abstract

“…Hambarde et al. [10] proposed an end‐to‐end sparse‐to‐dense network (S2DNet) for single image depth estimation. Herrera et al.…”

Section: Introductionmentioning

confidence: 99%

“…He et al [9] proposed a novel deep neural network to infer depth through effectively fusing the middle-level information on the fixed-focal-length data set. Hambarde et al [10] proposed an end-to-end sparse-to-dense network (S2DNet) for single image depth estimation. Herrera et al [11] proposed an automatic learning-based 2D-3D image conversion approach, which estimates the depth of a colour query image using the prior knowledge provided by a repository of colour + depth images.…”

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

S2DNet: Depth Estimation From Single Image and Sparse Samples

Cited by 49 publications

References 61 publications

MobileXNet: An Efficient Convolutional Neural Network for Monocular Depth Estimation

MobileXNet: An Efficient Convolutional Neural Network for Monocular Depth Estimation

Monocular Depth Estimation with Sharp Boundary

An unsupervised monocular image depth prediction algorithm using Fourier domain analysis

Contact Info

Product

Resources

About