Adaptive Support-Weight Approach for Correspondence Search

By Kuk-jin Yoon, In-So Kweon. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2006

1,308 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/0bd3984c75ea99ab214b1dc72d2d487d652f7e25

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

Optical flow modeling and computation: A survey (2015, background): “They are derived from the bilateral ﬁl-ter, favoring small distances in the spatial and color spaces [281]: where r s and r c control the inﬂuence of spatial distance and color similarity.”
Cross-Based Local Stereo Matching Using Orthogonal Integral Images (2009, methodology): “This speed is dozens of times faster than the adaptive support weight method [8], which takes 60 s for the Tsukuba image on an AMD 2700+ machine.”
A Quantitative Analysis of Current Practices in Optical Flow Estimation and the Principles Behind Them (2013, background): “We draw ideas from [53,71,74] to define the weights according to their spatial distance, their color-value distance, and their occlusion state as”
Fast Edge-Preserving PatchMatch for Large Displacement Optical Flow (2014, neutral): “But [31] showed that a good local method can perform equally well.”
High-Accuracy Stereo Matching Based on Adaptive Ground Control Points (2015, methodology): “Similar to the bilateral filter, Yoon [4] weighted each pixel by measuring the space and color similarity between pixels.”
AANet: Adaptive Aggregation Network for Efficient Stereo Matching (2020, methodology): “Local stereo methods (either traditional [40, 12] or 2D/3D convolution based methods [20, 14]) usually perform window based cost aggregation:”
Fast cost-volume filtering for visual correspondence and beyond (2011, methodology): “Even more importantly, we are the best performing local stereo method outperforming even the original implementation of [31] (rank 32).”
Efficient Large-Scale Stereo Matching (2010, methodology): “Approaches based on adaptive support windows [12, 13] adjust the window size or adapt the pixel weighting within a fixed-size window to improve performance, especially close to border discontinuities.”
Review of Stereo Vision Algorithms: From Software to Hardware (2008, methodology): “This work exploits the color and distance proximity based weight assignment for the pixels inside a fixed support window as reported in (Yoon and Kweon 2006a).”
Multi-View Stereo: A Tutorial (2015, background): “More advanced filters exist that use spatially varying domains [205].”
A non-local cost aggregation method for stereo matching (2012, background): “However, the reconstruction accuracy is much lower than the full-kernel implementation [6].”
Ieee Transactions on Pattern Analysis and Machine Intelligence 1 Stereo Processing by Semi-global Matching and Mutual Information (methodology): “Some methods additionally weight each pixel within the window according to color similarity and proximity to the center pixel [10], [11].”
Constant Time Weighted Median Filtering for Stereo Matching and Beyond (2013, background): “As a byproduct, the fast weighted median filtering unleashes its potential in other applications that were hampered by high complexities.”
Robust stereo matching with surface normal prediction (2017, background): “These algorithms [21], [19], [13], [38] generally compute the disparity for each pixel independently, so the recovered disparity maps may easily have artifacts around textureless and occluded regions.”
Evaluation of Stereo Matching Costs on Images with Radiometric Differences (2009, neutral): “This excludes popular methods like the correlation-based weighting according to proximity and color similarity [39], since this is an aggregation approach rather than a new matching cost.”
Stereo Matching with Color-Weighted Correlation, Hierachical Belief Propagation and Occlusion Handling (2006, methodology): “The computation of our correlation volume is depicted as follows, which is mainly a review of the method presented in [27].”