CBMV: A Coalesced Bidirectional Matching Volume for Disparity Estimation

Batsos, Konstantinos; Cai, Changjiang; Mordohai, Philippos

doi:10.1109/cvpr.2018.00220

Cited by 65 publications

(37 citation statements)

References 50 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Besides hand-crafted methods, researchers also proposed many learned matching costs [29,13,21] and cost aggregation algorithms [1,19]. Zbontar and Lecun [29] first proposed to compute matching costs using neural networks.…”

Section: Learning Based Methodsmentioning

confidence: 99%

“…GC-Net [6] and PSMNet [2] construct concatenation-based feature volume and incorporate a 3D CNN to aggregate contextual features. There are also works [1,19] trying to aggregate evidence from multiple hand-crafted matching cost proposals. However, the above methods have several drawbacks.…”

Section: Introductionmentioning

confidence: 99%

“…The concatenation volume [6,2] requires more parameters in the following aggregation network to learn the similarity measurement function from scratch. [1,19] stills utilizes traditional matching costs and cannot be optimized end-to-end.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Group-Wise Correlation Stereo Network

Guo

Yang²,

Yang³

et al. 2019

2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

569

445

View full text Add to dashboard Cite

Stereo matching estimates the disparity between a rectified image pair, which is of great importance to depth sensing, autonomous driving, and other related tasks. Previous works built cost volumes with cross-correlation or concatenation of left and right features across all disparity levels, and then a 2D or 3D convolutional neural network is utilized to regress the disparity maps. In this paper, we propose to construct the cost volume by group-wise correlation. The left features and the right features are divided into groups along the channel dimension, and correlation maps are computed among each group to obtain multiple matching cost proposals, which are then packed into a cost volume. Group-wise correlation provides efficient representations for measuring feature similarities and will not lose too much information like full correlation. It also preserves better performance when reducing parameters compared with previous methods. The 3D stacked hourglass network proposed in previous works is improved to boost the performance and decrease the inference computational cost. Experiment results show that our method outperforms previous methods on Scene Flow, KITTI 2012, and KITTI 2015 datasets. The code is available at https: //github.com/xy-guo/GwcNet

show abstract

Section: Learning Based Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Group-Wise Correlation Stereo Network

Guo

Yang²,

Yang³

et al. 2019

2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

569

445

View full text Add to dashboard Cite

show abstract

“…Zabih and Woodfil [40] therefore proposed two non-parametric local transforms, referred to as rank and census transforms, to address the correspondences at the boundaries of objects. A recent attempt tried to combine different window-based matching techniques for stereo matching [1].…”

Section: Stereo Matching Costmentioning

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

“…In contrast, CNN can learn more robust and discriminative features from images so that it can produce an improved stereo matching cost. Most CNN methods [11], [12], [14], [15], [18], [21]- [23] take stereo matching as a supervised learning task and are exploited to learn the stereo matching cost of two image patches. Only a small number of CNN methods [17], [24], [25] take stereo matching costs as unsupervised learning task, but their accuracy is significantly lower than that of the supervised CNN methods.…”

Section: Introductionmentioning

confidence: 99%

Two-Branch Convolutional Sparse Representation for Stereo Matching

Cheng

Zhang

2021

IEEE Access

View full text Add to dashboard Cite

Supervised learning methods have been used to calculate the stereo matching cost in a lot of literature. These methods need to learn parameters from public datasets with ground truth disparity maps. Due to the heavy workload used to label the ground truth disparities, the available training data are limited, making it difficult to apply these supervised learning methods to practical applications. The two-branch convolutional sparse representation (TCSR) model is proposed in the paper. It learns the convolutional filter bank from stereo image pairs in an unsupervised manner, which reduces the redundancy of the convolution kernels. Based on the TCSR model, an unsupervised stereo matching cost (USMC), which does not rely on the truth ground disparity maps, is designed. A feasible iterative algorithm for the TCSR model is also given and its convergence is proven. Experimental results on four popular data sets and one monocular video clip show that the USMC has higher accuracy and good generalization performance.INDEX TERMS Stereo matching cost, two-branch convolutional sparse representation, alternating direction method of multipliers, sparse representation.

show abstract

CBMV: A Coalesced Bidirectional Matching Volume for Disparity Estimation

Cited by 65 publications

References 50 publications

Group-Wise Correlation Stereo Network

Group-Wise Correlation Stereo Network

Semi-Dense Stereo Matching Using Dual CNNs

Two-Branch Convolutional Sparse Representation for Stereo Matching

Contact Info

Product

Resources

About