3D cost aggregation with multiple minimum spanning trees for stereo matching

Li, Lincheng; Yu, Xin; Zhang, Shunli; Zhao, Xiaolin; Zhang, Li

doi:10.1364/ao.56.003411

Cited by 71 publications

(40 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Here we compare our method against the state-of-the-art methods on the Middlebury benchmark dataset. We consider the top five methods from the Middlebury benchmark table: LocalExp [33], 3DMST [20], PMSC [21], MeshStere-oExt [44], NTDE [13]. Our algorithm achieves similar results as state-of-the-art for average (avrg), root-mean-squared (rms), A90, and A95 error metrics.…”

Section: A Comparison To State-of-the-art Methodsmentioning

confidence: 99%

“…In the paper [20], the authors propose a cost-aggregation method that embeds a minimum spanning tree based support region filtering in the general procedure. Furthermore, it combines this approach with a PatchMatch 3D label search, thus performing the search process with an adaptive patch size.…”

Section: A Contributionsmentioning

confidence: 99%

“…LocalExp [33] 3DMST [20] PMSC [21] MeshStr [44] NTDE [13] Adirondack Motorcycle PianoL Recycle Teddy Here we compare our method with the other top five methods. We take the example stereo images and the resultant disparity maps from the Middlebury benchmark V3 training set.…”

Section: Gt Ovod (Our)mentioning

confidence: 99%

See 2 more Smart Citations

One-View Occlusion Detection for Stereo Matching With a Fully Connected CRF Model

Mozerov

Weijer

2019

IEEE Trans. on Image Process.

View full text Add to dashboard Cite

In this paper, we extend the standard belief propagation (BP) sequential technique proposed in the tree-reweighted sequential method [15] to the fully connected CRF models with the geodesic distance affinity. The proposed method has been applied to the stereo matching problem. Also a new approach to the BP marginal solution is proposed that we call one-view occlusion detection (OVOD). In contrast to the standard winner takes all (WTA) estimation, the proposed OVOD solution allows to find occluded regions in the disparity map and simultaneously improve the matching result. As a result we can perform only one energy minimization process and avoid the cost calculation for the second view and the left-right check procedure. We show that the OVOD approach considerably improves results for cost augmentation and energy minimization techniques in comparison with the standard one-view affinity space implementation. We apply our method to the Middlebury data set and reach state-ofthe-art especially for median, average and mean squared error metrics.

show abstract

Section: A Comparison To State-of-the-art Methodsmentioning

confidence: 99%

Section: A Contributionsmentioning

confidence: 99%

See 1 more Smart Citation

One-View Occlusion Detection for Stereo Matching With a Fully Connected CRF Model

Mozerov

Weijer

2019

IEEE Trans. on Image Process.

View full text Add to dashboard Cite

show abstract

“…Since our model, especially our data term borrowed from [5], does not consider such new difficulties, we here slightly modify our model for adapting it to the latest benchmark. To this end, we incorporate the state-of-the-art CNN-based matching cost function by Zbontar and LeCun [49], by following manners of current top methods [10], [20], [28], [29] on the latest benchmark. Here, we only replace our pixelwise raw matching cost function ρ(·) of Eq.…”

Section: Evaluation On the Middlebury Benchmark V3mentioning

confidence: 99%

Continuous 3D Label Stereo Matching Using Local Expansion Moves

Taniai

Matsushita

Sato

et al. 2018

IEEE Trans. Pattern Anal. Mach. Intell.

121

128

View full text Add to dashboard Cite

Abstract-We present an accurate stereo matching method using local expansion moves based on graph cuts. This new move-making scheme is used to efficiently infer per-pixel 3D plane labels on a pairwise Markov random field (MRF) that effectively combines recently proposed slanted patch matching and curvature regularization terms. The local expansion moves are presented as many α-expansions defined for small grid regions. The local expansion moves extend traditional expansion moves by two ways: localization and spatial propagation. By localization, we use different candidate α-labels according to the locations of local α-expansions. By spatial propagation, we design our local α-expansions to propagate currently assigned labels for nearby regions. With this localization and spatial propagation, our method can efficiently infer MRF models with a continuous label space using randomized search. Our method has several advantages over previous approaches that are based on fusion moves or belief propagation; it produces submodular moves deriving a subproblem optimality; it helps find good, smooth, piecewise linear disparity maps; it is suitable for parallelization; it can use cost-volume filtering techniques for accelerating the matching cost computations. Even using a simple pairwise MRF, our method is shown to have best performance in the Middlebury stereo benchmark V2 and V3.

show abstract

“…CBMV disparity map Figure 1. The left view of Djembe stereo dataset [34] along with the disparity map computed by CBMV [2,6,8,15,18,37,38,43]. Our goal is similar to MC-CNN, since we also aim to estimate a matching volume that can be used as input to various optimization algorithms enabling them to produce highly accurate disparity maps.…”

Section: Djembementioning

confidence: 99%

CBMV: A Coalesced Bidirectional Matching Volume for Disparity Estimation

Batsos

Cai

Mordohai

2018

2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition

View full text Add to dashboard Cite

Recently, there has been a paradigm shift in stereo matching with learning-based methods achieving the best results on all popular benchmarks. The success of these methods is due to the availability of training data with ground truth; training learning-based systems on these datasets has allowed them to surpass the accuracy of conventional approaches based on heuristics and assumptions. Many of these assumptions, however, had been validated extensively and hold for the majority of possible inputs. In this paper, we generate a matching volume leveraging both data with ground truth and conventional wisdom. We accomplish this by coalescing diverse evidence from a bidirectional matching process via random forest classifiers. We show that the resulting matching volume estimation method achieves similar accuracy to purely data-driven alternatives on benchmarks and that it generalizes to unseen data much better. In fact, the results we submitted to the KITTI and ETH3D benchmarks were generated using a classifier trained on the Middlebury 2014 dataset.

show abstract

3D cost aggregation with multiple minimum spanning trees for stereo matching

Cited by 71 publications

References 15 publications

One-View Occlusion Detection for Stereo Matching With a Fully Connected CRF Model

One-View Occlusion Detection for Stereo Matching With a Fully Connected CRF Model

Continuous 3D Label Stereo Matching Using Local Expansion Moves

CBMV: A Coalesced Bidirectional Matching Volume for Disparity Estimation

Contact Info

Product

Resources

About