Efficient Stereo Matching Leveraging Deep Local and Context Information

Ye, Xiaoqing; Li, Jiamao; Wang, Han; Huang, Hexiao; Zhang, Xiaolin

doi:10.1109/access.2017.2754318

Cited by 37 publications

(25 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In addition, another methods based on deep learning have made dramatic progress in geometric computer vision matching tasks, such as image splicing [31], image fusion [32], object detection [33]. Following from that deep learning-based certain matching tasks including key point detection and feature registration [34], image patch matching [35], and stereo matching [36]. We focus on key point detection and feature registration related to our topic.…”

Section: Related Workmentioning

confidence: 99%

A Unified Framework for Nonrigid Point Set Registration via Coregularized Least Squares

Yang

Liu

et al. 2020

IEEE Access

View full text Add to dashboard Cite

This paper describes a method for performing nonrigid point set registration on data with different kinds of degradation (deformation, occlusion, noise, and outliers). We formulate the registration problem as a mixture model estimation problem by employing two topologically complementary constraints in a Gaussian mixture model (GMM)-based learning framework. The first constraint is Tikhonov-based regularization, which maintains the overall spatial connectivity by moving the point set collectively and coherently. The second constraint is graph-Laplacian-based regularization embedding, which preserves the intrinsic topological characteristics of the marginal space during registration. Hence, the proposed method is named coregularized least squares (Co-RLS). Our method iteratively estimates the correspondences and nonrigid transformation between two given sets of points. First, the correspondences are established subject to the ordering information of the contour points using feature descriptors, i.e., the shape context. Then, the transformation is recovered by minimizing the Co-RLS function, and the expectation maximization method is used to update the transformation parameters and outlier ratios. Experimental results on various types of synthetic and real data show the superior effectiveness and robustness of the proposed method compared with other state-of-the-art methods.

show abstract

Section: Related Workmentioning

confidence: 99%

A Unified Framework for Nonrigid Point Set Registration via Coregularized Least Squares

Yang

Liu

et al. 2020

IEEE Access

View full text Add to dashboard Cite

show abstract

“…Here, some important algorithms are reviewed. According to [3] and [20], a typical stereo matching algorithm consists of four steps: matching cost computation, cost aggregation, disparity computation, disparity refinement. SGM [21] is a real-time traditional algorithm for stereo matching, which is fast but do not produce good enough disparity maps.…”

Section: Related Workmentioning

confidence: 99%

“…It plays an important role in many computer vision applications, including autonomous vehicles [1], [2] and robotics. Given a rectified stereo pair of images, the purpose of stereo algorithm is to find correspondence of each pixel between two images along the same scan-line and compute the disparity for each pixel in the reference image [3]- [5].…”

Section: Introductionmentioning

confidence: 99%

Multi-Scale Context Attention Network for Stereo Matching

2019

View full text Add to dashboard Cite

Recently, many works for stereo matching with convolutional neural networks have gained satisfactory performance. However, it is still an urgent challenge to deal with ill-posed regions and improve details in disparity maps. To address these problems, we propose a multi-scale context attention network with three main modules: atrous spatial pyramid pooling attention, richer convolutional features, and attention mechanism. First, we propose an atrous spatial pyramid pooling attention module to capture context information by the aggregating context in different scales, meanwhile take advantage of the attention mechanism to selectively emphasize informative features and suppress fewer ones. Then, the richer convolutional module is proposed to bring useful detail information for the network. Additionally, attention mechanism is used to pick out informative features for disparity refinement sub-network. Furthermore, we design a point-specific loss function strategy to perform online hard point mining, which helps the network to improve the accuracy of disparity maps. The experiments on the FlyingThings3D and KITTI 2015 benchmark demonstrate that the proposed method can achieve state-of-the-art performance. INDEX TERMS Multi-scale, richer convolutional, atrous spatial pyramid pooling attention, attention mechanism, online hard point mining.

show abstract

“…Learning-based confidence measures have been successfully applied on detecting mismatches and further improving the accuracy of stereo matching [27]. Similar to the 2D CNN model for error detection proposed in [39], only left images and their disparity maps are selected to train our model. A key difference, however, is that no handcrafted operation is involved in our approach to fuse left and right disparity maps.…”

Section: Evaluation-netmentioning

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

Efficient Stereo Matching Leveraging Deep Local and Context Information

Cited by 37 publications

References 31 publications

A Unified Framework for Nonrigid Point Set Registration via Coregularized Least Squares

A Unified Framework for Nonrigid Point Set Registration via Coregularized Least Squares

Multi-Scale Context Attention Network for Stereo Matching

Semi-Dense Stereo Matching Using Dual CNNs

Contact Info

Product

Resources

About