Single-Image Depth Estimation Based on Fourier Domain Analysis

Lee, Jae-Han; Heo, Minhyeok; Kim, Kyung-Rae; Kim, Chang-Su

doi:10.1109/cvpr.2018.00042

Cited by 148 publications

(62 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For the method of Ma and Karaman [28], we show two results that are obtained from single RGB images alone and with partially known depths (200 pixels). The methods denoted without a superscript [9,16,40,25,2,3,24,21,32,10] and ours should be able to be compared in an equal condition.…”

Section: Performance Comparisonmentioning

confidence: 99%

Revisiting Single Image Depth Estimation: Toward Higher Resolution Maps With Accurate Object Boundaries

Özay

Zhang

et al. 2019

2019 IEEE Winter Conference on Applications of Computer Vision (WACV)

379

451

View full text Add to dashboard Cite

This paper considers the problem of single image depth estimation. The employment of convolutional neural networks (CNNs) has recently brought about significant advancements in the research of this problem. However, most existing methods suffer from loss of spatial resolution in the estimated depth maps; a typical symptom is distorted and blurry reconstruction of object boundaries. In this paper, toward more accurate estimation with a focus on depth maps with higher spatial resolution, we propose two improvements to existing approaches. One is about the strategy of fusing features extracted at different scales, for which we propose an improved network architecture consisting of four modules: an encoder, decoder, multi-scale feature fusion module, and refinement module. The other is about loss functions for measuring inference errors used in training. We show that three loss terms, which measure errors in depth, gradients and surface normals, respectively, contribute to improvement of accuracy in an complementary fashion. Experimental results show that these two improvements enable to attain higher accuracy than the current state-of-the-arts, which is given by finer resolution reconstruction, for example, with small objects and object boundaries.

show abstract

Section: Performance Comparisonmentioning

confidence: 99%

Revisiting Single Image Depth Estimation: Toward Higher Resolution Maps With Accurate Object Boundaries

Özay

Zhang

et al. 2019

2019 IEEE Winter Conference on Applications of Computer Vision (WACV)

379

451

View full text Add to dashboard Cite

show abstract

“…For optimization, they introduced the reverse Huber loss function [23]. Lee et al [24] used the depth network to predict the depth gradient and took it as local cues, and then further estimated the global and coarse depth. Finally they integrated the complementary prediction into the unified depth CNN framework to estimate the final depth image.…”

Section: A Supervised Depth Estimationmentioning

confidence: 99%

Attention-Based Dense Decoding Network for Monocular Depth Estimation

Wang

Zhang

et al. 2020

IEEE Access

View full text Add to dashboard Cite

Depth estimation is a classic computer vision task and provides rich representation of objects and environment. In recent years, the performance of end-to-end depth estimation has been significantly improved. However, the stack of convolutions and pooling operations result in losing local detail spatial information, which is extremely important to monocular depth estimation. In order to overcome this problem, in this work, we propose an encoder-decoder framework with skip connections. Based on the self-attention mechanism, we apply the channel-spatial attention module as a transition layer, which captures the depth and spatial positional relationship and improves the presentation ability of channel and space. Then we propose a dense decoding module to make full use of the attention features of different scale ranges in the decoding process. It achieves a more massive and denser receptive field while obtaining multi-scale information. Finally, a novel distance-aware loss is introduced to predict more meticulous edges and local details in the distance. Experiments demonstrate that the proposed method outperforms the state-of-the-art on KITTI and NYU Depth V2 datasets. INDEX TERMS Atrous spatial pyramid pooling, depth estimation, self-attention, dense decoding module.

show abstract

“…In [5], deep convolutional neural networks (DCNNs) involved ordinal regression into a dense prediction task by a spacing-increasing discretization strategy, and combined with dilated convolutions to obtain large receptive fields. The related works also have explored different loss functions for learning depth estimation, for instance, the reverse Huber function [4], the Structural Similarity (SSIM) index [14], Depth-Balanced Euclidean (DBE) loss [18], etc.…”

Section: A Unsupervised Depth Estimationmentioning

confidence: 99%

Efficient and High-Quality Monocular Depth Estimation via Gated Multi-Scale Network

et al. 2020

View full text Add to dashboard Cite

The key issue in monocular depth estimation is how to construct the depth image better and improve the quality of the depth map. At present, most of the monocular depth estimation methods based on deep learning manipulate images at low resolution that leads to loss of detail and blurring of boundaries. Nevertheless, deep learning with a large number of parameters needs highly computational complexity, which makes it difficult to apply high-resolution (HR) images to the depth estimate. In this work, model accuracy and runtime are two important factors to be considered. To improve the depth map quality and reduce the running time of the network, we introduce super-resolution techniques as methods of up-sampling to generate high-quality depth images at a faster rate for the depth estimation network. A novel approach is proposed for collecting high-level features that are captured under different receptive fields. The gated multi-scale decoder allows us to effectively filter information by the gated module. By combining the gated module to aid the super resolution of depth images, our method reduces memory consumption while improves reconstruction quality. Experiment results on the challenging NYU Depth v2 dataset demonstrate that both contributions provide significant performance gains over the state-of-the-art in self-supervised depth estimation.

show abstract

Single-Image Depth Estimation Based on Fourier Domain Analysis

Cited by 148 publications

References 24 publications

Revisiting Single Image Depth Estimation: Toward Higher Resolution Maps With Accurate Object Boundaries

Revisiting Single Image Depth Estimation: Toward Higher Resolution Maps With Accurate Object Boundaries

Attention-Based Dense Decoding Network for Monocular Depth Estimation

Efficient and High-Quality Monocular Depth Estimation via Gated Multi-Scale Network

Contact Info

Product

Resources

About