scholarly journals Evaluation of a New Coarse-to-Fine Strategy for Fast Semi-Global Stereo Matching

2011 ◽  
pp. 395-406 ◽  
Author(s):  
Simon Hermann ◽  
Reinhard Klette
Keyword(s):  
Stereo Matching ◽  
Coarse To Fine

Detail Preserving Coarse-to-Fine Matching for Stereo Matching and Optical Flow

2021 ◽  
pp. 1-1
Author(s):  
Yong Deng ◽  
Jimin Xiao ◽  
Steven Zhiying Zhou ◽  
Jiashi Feng
Keyword(s):  
Optical Flow ◽  
Stereo Matching ◽  
Coarse To Fine

scholarly journals A Joint 2D-3D Complementary Network for Stereo Matching

Sensors ◽  
2021 ◽  
Vol 21 (4) ◽  
pp. 1430
Author(s):  
Xiaogang Jia ◽  
Wei Chen ◽  
Zhengfa Liang ◽  
Xin Luo ◽  
Mingfei Wu ◽  
...  
Keyword(s):  
Stereo Matching ◽  
Computational Cost ◽  
Research Field ◽  
Disparity Map ◽  
Improve Performance ◽  
Cost Aggregation ◽  
Disparity Range ◽  
Public Datasets ◽  
Coarse To Fine ◽  
Speed And Accuracy

Stereo matching is an important research field of computer vision. Due to the dimension of cost aggregation, current neural network-based stereo methods are difficult to trade-off speed and accuracy. To this end, we integrate fast 2D stereo methods with accurate 3D networks to improve performance and reduce running time. We leverage a 2D encoder-decoder network to generate a rough disparity map and construct a disparity range to guide the 3D aggregation network, which can significantly improve the accuracy and reduce the computational cost. We use a stacked hourglass structure to refine the disparity from coarse to fine. We evaluated our method on three public datasets. According to the KITTI official website results, Our network can generate an accurate result in 80 ms on a modern GPU. Compared to other 2D stereo networks (AANet, DeepPruner, FADNet, etc.), our network has a big improvement in accuracy. Meanwhile, it is significantly faster than other 3D stereo networks (5× than PSMNet, 7.5× than CSN and 22.5× than GANet, etc.), demonstrating the effectiveness of our method.

Ambiguous Region Matching and Boundary Pixel Optimization for Stereo Computation

2012 ◽  
Vol 546-547 ◽  
pp. 735-740
Author(s):  
Xing Nian Cui ◽  
Fan Yang ◽  
Qing Min Liao
Keyword(s):  
Stereo Matching ◽  
Belief Propagation ◽  
Mean Shift ◽  
Mixed Pixel ◽  
Region Matching ◽  
Mixed Pixels ◽  
Belief Propagation Algorithm ◽  
The Mean ◽  
Boundary Pixel ◽  
Coarse To Fine

In this paper, we present a stereo matching algorithm based on planar surface hypothesis. It improves the results of low texture regions and mixed pixels on object boundaries. First, regions are segmented by applying the mean-shift segmentation method. Then we propose a coarse-to-fine algorithm to increase the reliable correspondences in low texture regions. Third, the Belief Propagation algorithm is used to optimize disparity plane labeling. Finally, for a mixed pixel, we utilize the results of the depth plane and the local region of it to regulate its disparity. Experimental results using the Middlebury stereo test show that the performance of our method is high.

Coarse-to-fine least squares stereo matching for 3-D reconstruction

1990 ◽  
Vol 26 (12) ◽  
pp. 812 ◽  
Author(s):  
F. Argenti ◽  
L. Alparone
Keyword(s):  
Least Squares ◽  
Stereo Matching ◽  
Coarse To Fine

scholarly journals Fast global stereo matching via energy pyramid minimization

2014 ◽  
Vol II-3 ◽  
pp. 41-48
Author(s):  
B. Conejo ◽  
S. Leprince ◽  
F. Ayoub ◽  
J. P. Avouac
Keyword(s):  
Random Fields ◽  
Stereo Matching ◽  
Conditional Random Fields ◽  
Optimal Solution ◽  
Stereo Pair ◽  
Optimization Approach ◽  
Disparity Map ◽  
Image Pyramids ◽  
Global Matching ◽  
Coarse To Fine

We define a global matching framework based on energy pyramid, the Global Matching via Energy Pyramid (GM-EP) algorithm, which estimates the disparity map from a single stereo-pair by solving an energy minimization problem. We efficiently address this minimization by globally optimizing a coarse to fine sequence of sparse Conditional Random Fields (CRF) directly defined on the energy. This global discrete optimization approach guarantees that at each scale we obtain a near optimal solution, and we demonstrate its superiority over state of the art image pyramid approaches through application to real stereo-pairs. We conclude that multiscale approaches should be build on energy pyramids rather than on image pyramids.

scholarly journals Accurate hierarchical stereo matching based on 3D plane labeling of superpixel for stereo images from rovers

2021 ◽  
Vol 18 (2) ◽  
pp. 172988142110021
Author(s):  
Haichao Li ◽  
Zhi Li ◽  
Jianbin Huang ◽  
Bo Meng ◽  
Zhimin Zhang
Keyword(s):  
Large Scale ◽  
Stereo Matching ◽  
State Of The Art ◽  
The State ◽  
Normal Vector ◽  
Stereo Images ◽  
Disparity Map ◽  
Matching Method ◽  
Search Range ◽  
Coarse To Fine

An accurate hierarchical stereo matching method is proposed based on continuous 3D plane labeling of superpixel for rover’s stereo images. This method can infer the 3D plane label of each pixel combined with the slanted-patch matching strategy and coarse-to-fine constraints, which is especially suitable for large-scale scene matching with low-texture or textureless regions. At every level, the stereo matching method based on superpixel segmentation makes the iteration convergence faster and avoids huge redundant computations. In the coarse-to-fine matching scheme, we propose disparity constraint and 3D normal vector constraint between adjacent levels through which the disparity map and 3D normal vector map at a coarser level are used to restrict the search range of disparity and normal vector at a fine level. The experimental results with the Chang’e-3 rover dataset and the KITTI dataset show that the proposed stereo matching method is efficiently and accurately compared with the state-of-the-art 3D labeling algorithm, especially in low-texture or textureless regions. The computational efficiency of this method is about five to six times faster than the state-of-the-art 3D labeling method, and the accuracy is better.

Sign in / Sign up

Export Citation Format

Share Document