Symmetric stereo matching for occlusion handling

By Yin Li, Sing Bing Kang. Computer Vision and Pattern Recognition, 2005

502 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/9fe7974d7cae830d5a10594fc205785292a5ad2b

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

Citations in the corpus

Stereo for Image-Based Rendering using Image Over-Segmentation (2007, methodology): “In other words, when computing equations (10) and (12) for image i with respect to image j, the value of p jπ(x,d) (d) is computed without knowledge of image i's MRF.”
Pixelwise View Selection for Unstructured Multi-View Stereo (2016, background): “MVS leverages multiple views to overcome the inherent occlusion problems of two-view approaches [49, 53, 62].”
Self-Supervised Monocular Depth Estimation: Solving the Dynamic Object Problem by Semantic Guidance (2020, methodology): “equential images. Afterwards we review how the dynamic object problem has been approached in multi-task learning settings. Depth Estimation: Before the emergence of neural networks, stereo algorithms [26,52] and structure from motion [1,48] were used to infer depth from stereo image pairs or a serie”
Particle Belief Propagation (2009, methodology): “Belief propagation was applied to the stereo vision problem in Sun et al. (2003), and since then a number of more sophisticated models have also used BP for inference (e.g., Sun et al., 2005; Klaus et al., 2006; Yang et al., 2006).”
Compositional Convolutional Neural Networks: A Robust and Interpretable Model for Object Recognition Under Occlusion (2020, background): “Other approaches focus on videos or stereo images [34,23].”
Learning Conditional Random Fields for Stereo (2007, methodology): “[10], which uses BP and an explicit occlusion model.”
High-Accuracy Stereo Matching Based on Adaptive Ground Control Points (2015, background): “Convergent process on Slant image [32] with textureless foreground and front parallel background.”
Ieee Transactions on Pattern Analysis and Machine Intelligence 1 Stereo Processing by Semi-global Matching and Mutual Information (methodology): “Consequently, most of these methods have runtimes of more than 20 seconds [3], [12] to more than a minute [9]–[11], [13], [14] on the test images.”
Consistent Depth Maps Recovery from a Video Sequence (2009, methodology): “Multiview stereo algorithms [28], [6], [19], [52], [16] estimate depth (or disparity) with the input of multiple images.”
Stereo Matching with Color-Weighted Correlation, Hierachical Belief Propagation and Occlusion Handling (2006, methodology): “The stereo algorithm presented in this paper springs from the popular energy minimization framework that is the basis for most highperformance algorithms, such as graph cuts [4], [16] and belief propagation [19], [20].”
Deep Occlusion-Aware Instance Segmentation with Overlapping BiLayers (2021, unknown): “Occlusion Handling Methods for occlusion handling have been proposed [50, 57, 17, 10, 60, 23, 17, 65, 59].”
Real-Time Plane-Sweeping Stereo with Multiple Sweeping Directions (2007, background): “More sophisticated algorithms based on graph cuts [10 ] and belief propagation [15 ] offer improved results for textureless areas and occlusion handling, but at a heavy performance penalty.”
Fusion of time-of-flight depth and stereo for high accuracy depth maps (2008, methodology): “The current state of the art in stereo matching is achieved by global optimization algorithms (e.g., [15, 13 , 25]).”
Segment-Based Stereo Matching Using Belief Propagation and a Self-Adapting Dissimilarity Measure (2006, background): “Stereo matching continues to be an active research area as is proven by a large number of recent publications dedicated to this topic [1, 2, 4, 6, 9, 12].”
Global stereo reconstruction under second order smoothness priors (2008, methodology): “between optimizing visibility and optimizing depth [14], [35].”
Occlusion Aware Unsupervised Learning of Optical Flow (2017, background): “The second group deals with occlusion by exploiting the symmetric property of optical flow and ignoring the loss penalty on predicted occluded regions [51, 2, 25].”
Iterative Residual Refinement for Joint Optical Flow and Occlusion Estimation (2019, background): “Occlu sion estimates can enable (i) a more accurate matching cost [50, 57, 60], (ii) bi-directional consistency [25, 28], or (iii) uniqueness constraints for pixel-level matching [2, 25, 54].”
Using Multiple Hypotheses to Improve Depth-Maps for Multi-View Stereo (2008, background): “This may be via an explicit estimation of a disparity map, for example [20] or internally as part of an optimisation routine [4].”