DPNet: Detail-preserving network for high quality monocular depth estimation

Ye, Xinchen; Shu-de, Chen; Xu, Rui

doi:10.1016/j.patcog.2020.107578

Cited by 37 publications

(28 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The depth results state that our approach is significantly superior to Roxas and Oishi, 15 Graber et al, 17 and Hu and Chen. 29 Moreover, contrast to some current prominent CNN methods, [20][21][22][23][24][25][26][27][28] our method uses stereo information and given ground truth pose, the results in Table 2 show that our approach can reach the performance of state-of-the-art methods. The estimated visualize depth results are presented in Figure 2.…”

Section: Kitti Datasetmentioning

confidence: 90%

A variational approach for estimation of monocular depth and camera motion in autonomous driving

Zhang

2021

Proceedings of the Institution of Mechanical Engineers, Part D:

View full text Add to dashboard Cite

In this paper, a new direct computational approach to dense 3D reconstruction in autonomous driving is proposed to simultaneously estimate the depth and the camera motion for the motion stereo problem. A traditional Structure from Motion framework is utilized to establish geometric constrains for our variational model. The architecture is mainly composed of the texture constancy constraint, one-order motion smoothness constraint, a second-order depth regularize constraint and a soft constraint. The texture constancy constraint can improve the robustness against illumination changes. One-order motion smoothness constraint can reduce the noise in estimation of dense correspondence. The depth regularize constraint is used to handle inherent ambiguities and guarantee a smooth or piecewise smooth surface, and the soft constraint can provide a dense correspondence as initial estimation of the camera matrix to improve the robustness future. Compared to the traditional dense Structure from Motion approaches and popular stereo approaches, our monocular depth estimation results are more accurate and more robust. Even in contrast to the popular depth from single image networks, our variational approach still has good performance in estimation of monocular depth and camera motion.

show abstract

Section: Kitti Datasetmentioning

confidence: 90%

A variational approach for estimation of monocular depth and camera motion in autonomous driving

Zhang

2021

Proceedings of the Institution of Mechanical Engineers, Part D:

View full text Add to dashboard Cite

show abstract

“…To evaluate the performance of our proposed method, we conduct experiments in various settings on two benchmark datasets, i.e., the KITTI dataset for outdoor scenario and the NYU Depth V2 dataset for indoor scenario. We provide both quantitative results and qualitative results for our method, as well as compare results with other leading monocular depth estimation methods, i.e., [ 6 , 7 , 17 , 20 , 21 , 28 , 30 , 44 , 58 , 64 , 65 , 66 , 67 ].…”

Section: Methodsmentioning

confidence: 99%

“…The quantitative results on the KITTI Eigen test split are shown in Table 2 , where [ 20 , 28 , 30 , 44 , 69 , 71 , 72 ] adopted the same split strategy as our method. It is worth noting that Lee et al [ 20 ] devised a pyramid-like decoder with an encoder the same as ours, ResNeXt101.…”

Section: Methodsmentioning

confidence: 99%

“…Ye et al. [ 28 ] proposed a dual-branch network to preserve the spatial and context information of features for monocular depth estimation task. According to the training manners, DNN models can be sorted into three types: supervised [ 5 , 7 , 20 , 21 ], unsupervised [ 29 , 30 , 31 , 32 ] and semi-supervised [ 33 , 34 , 35 ].…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

DCPNet: A Densely Connected Pyramid Network for Monocular Depth Estimation

Lai

Tian

et al. 2021

Sensors

View full text Add to dashboard Cite

Pyramid architecture is a useful strategy to fuse multi-scale features in deep monocular depth estimation approaches. However, most pyramid networks fuse features only within the adjacent stages in a pyramid structure. To take full advantage of the pyramid structure, inspired by the success of DenseNet, this paper presents DCPNet, a densely connected pyramid network that fuses multi-scale features from multiple stages of the pyramid structure. DCPNet not only performs feature fusion between the adjacent stages, but also non-adjacent stages. To fuse these features, we design a simple and effective dense connection module (DCM). In addition, we offer a new consideration of the common upscale operation in our approach. We believe DCPNet offers a more efficient way to fuse features from multiple scales in a pyramid-like network. We perform extensive experiments using both outdoor and indoor benchmark datasets (i.e., the KITTI and the NYU Depth V2 datasets) and DCPNet achieves the state-of-the-art results.

show abstract

“…Specifically, encoded features were fed into different streams for decoding depth residuals. Ye et al [29] proposed DPNet for high-quality monocular depth estimation. They designed an efficient non-local spatial attention module and a spatial branch (SB) to preserve spatial information.…”

Section: Related Workmentioning

confidence: 99%

Detail-preserving depth estimation from a single image based on modified fully convolutional residual network and gradient network

Liu

2021

SN Appl. Sci.

View full text Add to dashboard Cite

Predicting a convincing depth map from a monocular single image is a daunting task in the field of computer vision. In this paper, we propose a novel detail-preserving depth estimation (DPDE) algorithm based on a modified fully convolutional residual network and gradient network. Specifically, we first introduce a new deep network that combines the fully convolutional residual network (FCRN) and a U-shaped architecture to generate the global depth map. Meanwhile, an efficient feature similarity-based loss term is introduced for training this network better. Then, we devise a gradient network to generate the local details of the scene based on gradient information. Finally, an optimization-based fusion scheme is proposed to integrate the depth and depth gradients to generate a reliable depth map with better details. Three benchmark RGBD datasets are evaluated from the perspective of qualitative and quantitative, the experimental results show that the designed depth prediction algorithm is superior to several classic depth prediction approaches and can reconstruct plausible depth maps.

show abstract

DPNet: Detail-preserving network for high quality monocular depth estimation

Cited by 37 publications

References 16 publications

A variational approach for estimation of monocular depth and camera motion in autonomous driving

A variational approach for estimation of monocular depth and camera motion in autonomous driving

DCPNet: A Densely Connected Pyramid Network for Monocular Depth Estimation

Detail-preserving depth estimation from a single image based on modified fully convolutional residual network and gradient network

Contact Info

Product

Resources

About