A Deep Visual Correspondence Embedding Model for Stereo Matching Costs

Chen, Zhuoyuan; Sun, Xingming; Wang, Liang; Yan, Yu; Huang, Chang

doi:10.1109/iccv.2015.117

Cited by 205 publications

(142 citation statements)

References 26 publications

Supporting

Mentioning

142

Contrasting

Order By: Relevance

“…As a result, the receptive field is restricted to a relatively small size. For example, the patch sizes in [1], [3], [5] are 9 × 9, 11 × 11 and 13 × 13, respectively. They are prone to be ambiguous and produce a noisy matching cost in weakly-textured areas due to limited local context information.…”

Section: Feature Ensemble Networkmentioning

confidence: 99%

“…Luo et al [5] improved the architecture by means of treating it as a multi-label classification problem, in which the labels were all possible disparities. Chen et al [3] computed two similarity scores separately based on the multi-scale patch pairs and then a fusion was made for the final decision.…”

Section: Introductionmentioning

confidence: 99%

“…Nevertheless, poor performance was reported in large textureless areas, owing to limited local information with small 11 × 11 receptive field [1]. 13 × 13 patches of different resolutions were taken as input of two unattached subnetworks [3]. However, the similarity score of each network was simply fused for final decision.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Feature Ensemble Network with Occlusion Disambiguation for Accurate Patch-Based Stereo Matching

Wang

et al. 2017

IEICE Trans. Inf. & Syst.

View full text Add to dashboard Cite

SUMMARYAccurate stereo matching remains a challenging problem in case of weakly-textured areas, discontinuities and occlusions. In this letter, a novel stereo matching method, consisting of leveraging feature ensemble network to compute matching cost, error detection network to predict outliers and priority-based occlusion disambiguation for refinement, is presented. Experiments on the Middlebury benchmark demonstrate that the proposed method yields competitive results against the state-of-the-art algorithms. key words: stereo matching, convolutional neural network, patch-based, occlusion disambiguation

show abstract

Section: Feature Ensemble Networkmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Feature Ensemble Network with Occlusion Disambiguation for Accurate Patch-Based Stereo Matching

Wang

et al. 2017

IEICE Trans. Inf. & Syst.

View full text Add to dashboard Cite

show abstract

“…Cross-based cost aggregation and semi-global matching are preformed for the obtained cost-volume to produce accurate disparity map. To speed up computing the matching cost, Chen et al [11] and Luo et al [23] proposed similar ideas, where the matching cost is defined as the inner product of two features from CNN. In FlowNet [13], the matching costs are defined as the correlation between two patches of feature maps, and the final flow map is obtained by upconvolution operation.…”

Section: Cost Aggregation Methods For Labeling Problemsmentioning

confidence: 99%

“…Recently, Zhan et al [48] proposed some techniques for local stereo matching methods to improve the accuracy: mask filtering as a pre-processing, an improved matching cost function, and multi-step disparity refinement as a post-processing. Inspired by the great success of convolutional neural networks (CNNs) in image recognition task, CNNs are recently used for computing the label costs (matching costs in stereo matching and optical flow estimation) instead of hand-crafted cost functions [11,13,23,46,47], which has led to significant improvement in terms of accuracy. In MC-CNN [46,47], the CNN directly outputs the matching cost of two input patches.…”

Section: Cost Aggregation Methods For Labeling Problemsmentioning

confidence: 99%

Efficiency-enhanced cost-volume filtering featuring coarse-to-fine strategy

Furuta

Ikehata

Yamaskai

et al. 2017

Multimed Tools Appl

View full text Add to dashboard Cite

Cost-volume filtering (CVF) is one of the most widely used techniques for solving general multi-labeling problems based on a Markov random field (MRF). However it is inefficient when the label space size (i.e., the number of labels) is large. This paper presents a coarse-to-fine strategy for cost-volume filtering that efficiently and accurately addresses multi-labeling problems with a large label space size. Based on the observation that true labels at the same coordinates in images of different scales are highly correlated, we truncate unimportant labels for cost-volume filtering by leveraging the labeling output of lower scales. Experimental results show that our algorithm achieves much higher efficiency than the original CVF method while maintaining a comparable level of accuracy. Although we performed experiments that deal with only stereo matching and optical flow estimation, the proposed method can be employed in many other applications because of the applicability of CVF to general discrete pixel-labeling problems based on an MRF.

show abstract

Stereo Matching with Multi‐scale Based on Anisotropic Match Cost

Liu

Cai

Zhou

et al. 2020

Concurrency and Computation

View full text Add to dashboard Cite

Binocular vision is a popular method for 3d measurement, but the precision and efficiency is still a limitation. In order to solve the problem of low precision and high mismatching rate of current stereo match methods in weak texture region, a local stereo matching algorithm with multi-scale based on anisotropic match cost was proposed. Not only including the gray value between the adjacent pixels as the absolute difference (AD) method, the matching cost function also involved gradient and phase information to make an anisotropic evaluation and eliminate the outliers of the flat area. Meanwhile, a multi-scale strategy with the image pyramid was referenced, and the dynamic disparity search range of variable window was used on the original cost aggregation framework by improving the stereo matching algorithm of cross-scale cost aggregation. The matching cost volume in each scale space used the dynamic support window to guide the filter to aggregate the matching cost. Finally, to overcome the problems of disparity selection ambiguity of WTA (winner-take-all) strategy and the horizontal fringe introduced by left-right consistency (LRC) detection, the weighted median filter based on guided filter weight was used to carry out disparity refinement. According to the experiments, the method got more high matching accuracy, and the average error on the Middlebury test platform reached 5.25%.

show abstract

A Deep Visual Correspondence Embedding Model for Stereo Matching Costs

Cited by 205 publications

References 26 publications

Feature Ensemble Network with Occlusion Disambiguation for Accurate Patch-Based Stereo Matching

Feature Ensemble Network with Occlusion Disambiguation for Accurate Patch-Based Stereo Matching

Efficiency-enhanced cost-volume filtering featuring coarse-to-fine strategy

Stereo Matching with Multi‐scale Based on Anisotropic Match Cost

Contact Info

Product

Resources

About