Disparity Estimation by Simultaneous Edge Drawing

Pena, Dexmont; Sutherland, Alistair

doi:10.1007/978-3-319-54427-4_10

Cited by 12 publications

(9 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The MT-TW-SMNet achieved better overall tele-wide disparity estimation accuracy than the SIDENet. Our multitask tele-wide disparity estimation also ranks on the KITTI leader board better than other methods which use full wide left and right images for stereo disparity estimation, such as [50]- [52]. The table also shows that with fusion between the different methods (MT-TW Fusion), the result can be further improved so the overall disparity error is only 11.96% 1 .…”

Section: B Performance Comparisons Between Tw-smnet Shg-sidenet Anmentioning

confidence: 80%

Multitask Deep Neural Networks for Tele-Wide Stereo Matching

El-Khamy

Ren

et al. 2020

IEEE Access

View full text Add to dashboard Cite

In this paper, we propose deep learning solutions for the estimation of the real world depth of elements in a scene captured by two cameras with different field of views. We consider a realistic smartphone scenario, where the first field of view (FOV) is a wide FOV with 1× the optical zoom, and the second FOV is contained in the first FOV captured by a tele zoom lens with 2× the optical zoom. We refer to the problem of estimating the depth for all elements in the union of the FOVs which corresponds to the Wide FOV as 'tele-wide stereo matching'. Traditional approaches can only estimate the disparity or depth in the overlapped FOV, corresponding to the Tele FOV, using stereo matching algorithms. To benchmark this novel problem, we introduce a single-image inverse-depth estimation (SIDE) solution to estimate the disparity from the image corresponding to the union Wide FOV only. We also design a novel multitask tele-wide stereo matching deep neural network (MT-TW-SMNet), which is the first to combine the stereo matching and the single image depth tasks in one network. Moreover, we propose multiple methods for the fusion between the above networks. For example, we have input feature fusion, that utilizes the disparity estimated by stereo-matching as an additional input feature for SIDE. We also designed networks for decision fusion, that deploys a stacked hour glass (SHG) network for fusion and refinement of the disparity maps from both the SIDE network and the MT-TW-SMNet. These fusion schemes significantly improve the accuracy. Experimental results on KITTI and SceneFlow datasets demonstrate that our proposed approaches provide a reasonable solution to the tele-wide stereo matching problem. We demonstrate the effectiveness of our solutions in generating the Bokeh effect on the full Wide FOV.

show abstract

Section: B Performance Comparisons Between Tw-smnet Shg-sidenet Anmentioning

confidence: 80%

Multitask Deep Neural Networks for Tele-Wide Stereo Matching

El-Khamy

Ren

et al. 2020

IEEE Access

View full text Add to dashboard Cite

show abstract

“…The other one is to compare with SED (Simultaneous Edge Drawing) [ 19 ], another sparse matching method based on edges. The

of SED is

only.…”

Section: Methodsmentioning

confidence: 99%

“…Dexmont Peña et al [ 19 ] extended the Edge Drawing (ED) algorithm on stereo pairs, matched only a few anchor points and then propagated disparities along the edges. Using the proposed method, the number of computations can be greatly decreased.…”

Section: Related Workmentioning

confidence: 99%

“… Examples of comparison between our method and SED [ 19 ]. From top to bottom: the left images, the semantic edges, the disparity maps of the following methods separately: SAD + ADP (LRC), SAD + ADP (SLRC), Census + ADP (LRC), Census + ADP (SLRC), SAD + 0.1Census + ADP (LRC), SAD + 0.1Census + ADP (SLRC), SED [ 19 ], SED after interpolation. …”

Section: Figurementioning

confidence: 99%

See 1 more Smart Citation

Semantic Edge Based Disparity Estimation Using Adaptive Dynamic Programming for Binocular Sensors

Zhu

Wang

et al. 2018

Sensors

View full text Add to dashboard Cite

Disparity calculation is crucial for binocular sensor ranging. The disparity estimation based on edges is an important branch in the research of sparse stereo matching and plays an important role in visual navigation. In this paper, we propose a robust sparse stereo matching method based on the semantic edges. Some simple matching costs are used first, and then a novel adaptive dynamic programming algorithm is proposed to obtain optimal solutions. This algorithm makes use of the disparity or semantic consistency constraint between the stereo images to adaptively search parameters, which can improve the robustness of our method. The proposed method is compared quantitatively and qualitatively with the traditional dynamic programming method, some dense stereo matching methods, and the advanced edge-based method respectively. Experiments show that our method can provide superior performance on the above comparison.

show abstract

“…Since a large set of (a) training (b) testing Figure 9. Comparison with the top ten approaches on the Middlebury Stereo Evaluation site [29]: SED [23], R-NCC (unpublished work), r200high [15], ICSG [33], SGM [11], DF (unpublished work), MotionStereo (unpublished work), IDR [17], TMAP [28] and SNCC [6]. Performances of different approaches on both training (a) and testing (b) datasets are plotted on non-occlusion error rates v.s.…”

Section: Matching-net Evaluation-net Attributes Kernel Size Quantitymentioning

confidence: 99%

Semi-Dense Stereo Matching Using Dual CNNs

Mao

Wang

Zhou

et al. 2019

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

View full text Add to dashboard Cite

A robust solution for semi-dense stereo matching is presented. It utilizes two CNN models for computing stereo matching cost and performing confidence-based filtering, respectively. Compared to existing CNNs-based matching cost generation approaches, our method feeds additional global information into the network so that the learned model can better handle challenging cases, such as lighting changes and lack of textures. Through utilizing nonparametric transforms, our method is also more self-reliant than most existing semi-dense stereo approaches, which rely highly on the adjustment of parameters. The experimental results based on Middlebury Stereo dataset demonstrate that the proposed approach outperforms the state-of-the-art semi-dense stereo approaches.

show abstract

Disparity Estimation by Simultaneous Edge Drawing

Cited by 12 publications

References 20 publications

Multitask Deep Neural Networks for Tele-Wide Stereo Matching

Multitask Deep Neural Networks for Tele-Wide Stereo Matching

Semantic Edge Based Disparity Estimation Using Adaptive Dynamic Programming for Binocular Sensors

Semi-Dense Stereo Matching Using Dual CNNs

Contact Info

Product

Resources

About