Handling occlusions in dense multi-view stereo

By Sing Bing Kang, Richard Szeliski, Jinxiang Chai. Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001, 2001

441 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/48766e3ca12448a0b1f29a2ef68126023459a928

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

Real-Time Visibility-Based Fusion of Depth Maps (2007, background): “The minimum of the two sums is the cost of the depth hypothesis [9].”
Fast variable window for stereo correspondence using integral images (2003, methodology): “Another popular method [8, 5, 4, 10] is the multiple window.”
Consistent Depth Maps Recovery from a Video Sequence (2009, background): “Multiview stereo algorithms [28], [6], [19], [52], [16] estimate depth (or disparity) with the input of multiple images.”
A Comparison and Evaluation of Multi-View Stereo Reconstruction Algorithms (2006, methodology): “A heuristic often used in tandem with outlier rejection is to avoid comparing views that are far apart, thereby increasing the likely percentage of inliers [31, 34, 37, 38].”
Deep Stereo Using Adaptive Thin Volume Representation With Uncertainty Awareness (2019, background): “Multi-view stereo is a long-studied vision problem with many traditional approaches [44, 39, 33, 32, 26, 10, 8, 13, 43].”
Computing visual correspondence with occlusions using graph cuts (2001, methodology): “an “occluded” label to the algorithm, as [ 15 ] does.”
Real-Time Plane-Sweeping Stereo with Multiple Sweeping Directions (2007, background): “This scheme is very effective against occlusions, since typically the visibility of a pixel changes at most once in a sequence of images.”
Multi-View Stereo for Community Photo Collections (2007, background): “[13] exploit the assumption that the temporal order of images matches the spatial order, and use shiftable windows in time to adaptively choose frames to match.”
Detailed Real-Time Urban 3D Reconstruction from Video (2007, methodology): “We use the absolute intensity difference as the dissimilarity measure and aggregate several measurements in a window W(x,y) centered at the pixel (x, y). To increase robustness against occlusion, we adopt an algorithm proposed by Kang et al. (2001) .”
Stereo Matching Using Belief Propagation (2002, neutral): “Some improved window-based methods, such as adaptive windows [20] and shiftable windows [6], [33], [21] try to avoid windows that span depth discontinuities.”
Segment based 3D object shape priors (2015, methodology): “For occlusion handling, we only accept the best K matching scores [11].”
Multi-camera Scene Reconstruction via Graph Cuts (2002, methodology): “While energy minimization has been widely used for stereo, only a few papers [13, 20, 24] have used it for scene reconstruction.”
Building Rome on a Cloudless Day (2010, background): “Our stereo deploys 20 matching views, and handles occlusions (and other outliers) through taking the best 50% of views per pixel as suggested in [34].”
Adaptive Support-Weight Approach for Correspondence Search (2006, neutral): “Index Terms—Stereo, 3D/stereo scene analysis.”
Stereo for Image-Based Rendering using Image Over-Segmentation (2007, background): “They range from being fixed (Okutomi and Kanade, 1993) and adaptive (Kanade and Okutomi, 1994) to shiftable (Okutomi et al., 2002) and with view selection (Kang et al., 2001).”
Pixelwise View Selection for Unstructured Multi-View Stereo (2016, background): “[38] heuristically select the best views with minimal cost (usually 50 %) for computing the depth of each pixel.”
Real-Time Direct Dense Matching on Fisheye Images Using Plane-Sweeping Stereo (2014, background): “There are different options to compute the aggregated cost, with the choice of taking occlusions into account [13].”
High-quality Image-based Interactive Exploration of Real-World Environments 1 (2003, positive): “We used the shiftable window technique [Kang et al. , 2001] in our stereo algorithm to handle occlusions in the overlap region.”