Multi-camera Scene Reconstruction via Graph Cuts

By Vladimir Kolmogorov, Ramin Zabih. European Conference on Computer Vision, 2002

911 citations recorded by the source corpus.

Subfields: Aerospace Engineering, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/390ba243bb7648369ba6e8fed313e9d6f53846bd

How researchers see this paper

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

In Aerospace Engineering

In Computer Vision and Pattern Recognition

Citations in the corpus

Modelling dynamic scenes by registering multi-view image sequences (2005, background): “Graph cuts algorithms yield a global minimum or a strong local minimum, and have proved to perform very well in some formulations of the stereovision problem [11], but they cannot be applied to an arbitrary energy function [12].”
A Comparative Study of Energy Minimization Methods for Markov Random Fields (2006, methodology): “We hope to investigate different grid topologies (such as the 8-connected topology for 2D, or 26-connected for 3D), as well as non-local topologies such as those used with multiple depth maps [43, 44].”
Cost Volume Pyramid Based Depth Inference for Multi-View Stereo (2019, methodology): “We refer to algorithms before deep learning era as traditional MVS methods which represent the 3D geometry of objects or scene using voxels [7, 23], level-sets [9, 31], polygon meshes [8, 10] or depth maps [18, 22].”
Algebraic Statistics for Computational Biology: Preface (2005, background): “Importantly, it has been shown that in the binary labeling case, when a solution exists, the non-integer linear relaxation is guaranteed to produce the integral optimal solution [Kolmogorov and Zabih, 2003].”
Multi-View Stereo Reconstruction and Scene Flow Estimation with a Global Image-Based Matching Score (2007, methodology): “In the last few years, this method has been successfully applied to several problems in computer vision, including stereovision [16] and image segmentation [2].”
PatchMatch Stereo - Stereo Matching with Slanted Support Windows (2011, methodology): “The data term is thereby taken from [8] and enables symmetrical occlusion handling.”
What energy functions can be minimized via graph cuts? (2002, methodology): “These methods have been successfully used for a wide variety of vision problems, including image restoration [9], [10], [18], [21], stereo and motion [4], [9], [10], [20], [24], [27], [32], [35], [36], image synthesis [29], image segmentation [8], voxel occupancy [39], multicamera scene reconstructi”
MVSNeRF: Fast Generalizable Radiance Field Reconstruction from Multi-View Stereo (2021, background): “Multi-view stereo (MVS) is a classical computer vision problem, aiming to achieve dense geometry reconstruction using images captured from multiple viewpoints, and has been extensively explored by various traditional methods [12, 24, 23, 14, 39, 16, 38].”
Cross-Based Local Stereo Matching Using Orthogonal Integral Images (2009, methodology): “It even achieves a better performance than some complex global stereo matching methods [16]–[18], as shown in Table III.”
High Accuracy and Visibility-Consistent Dense Multiview Stereo (2012, neutral): “The performance of some depth maps-based methods [36], [58], [56], [22], [57], [23], [24] for complete reconstruction, however, seems to be lower than previously discussed approaches, as regards either accuracy or completeness of the obtained model.”
A Comparison and Evaluation of Multi-View Stereo Reconstruction Algorithms (2006, methodology): “A number of methods define a volumetric MRF and use max-flow [6, 19, 47, 48] or multi-way graph cut [35] to extract an optimal surface.”
Multi-view stereo via volumetric graph-cuts (2005, background): “These problems are often formulated as minimisations of Markov Random Field (MRF) energy functions providing a clean and computationally-tractable formulation, for which good approximate solutions exist using Graph cuts [2, 7, 12, 6] or Loopy Belief Propagation [16].”
Semantic 3D Reconstruction with Continuous Regularization and Ray Potentials Using a Visibility Consistency Constraint (2016, background): “Visibility relations in 3D reconstructions were studied for computing a single depth map out of multiple images [14, 15].”
Convergent Tree-Reweighted Message Passing for Energy Minimization (2006, neutral): “stereo [3,14], image restoration [3], image segmentaion [2], texture synthesis [19].”
Efficient Multi-View Reconstruction of Large-Scale Scenes using Interest Points, Delaunay Triangulation and Graph Cuts (2007, methodology): “outdor architectural scenes) are those representing geometry by several depth maps [18, 17, 23, 37, 38, 39].”
Stereo correspondence by dynamic programming on a tree (2005, methodology): “Recently, graph-cuts [6, 15] and belief propagation methods [20, 9] have been applied quite successfully to optimize equation (1).”
Graph Cuts and Efficient N-D Image Segmentation (2006, background): “, 1998), multi-view reconstruction (Kolmogorov and Zabih, 2002; Vogiatzis et al., 2005; Lempitsky et al., 2006), texture synthesis (Kwatra et al.”