Modelling dynamic scenes by registering multi-view image sequences

By Jean-Philippe Pons, Renaud Keriven, Olivier D. Faugeras. 2005

145 citations recorded by the source corpus.

Subfields: Computer Graphics and Computer-Aided Design, Computer Vision and Pattern Recognition

How researchers see this paper

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

In Computer Graphics and Computer-Aided Design

In Computer Vision and Pattern Recognition

Citations in the corpus

Occupancy Networks: Learning 3D Reconstruction in Function Space (2018, background): “This idea is related to classical level set [10, 14, 50] approaches to multi-view 3D reconstruction [18,24,32,40,53,78].”
A Surface-Growing Approach to Multi-View Stereo Reconstruction (2007, methodology): “Level-set surface representations ([16, 20]) naturally support topology changes but controlling the correct topology is still a difﬁcult issue.”
A Comparison and Evaluation of Multi-View Stereo Reconstruction Algorithms (2006, methodology): “Comparing the predicted and measured images yields a photo-consistency measure known as prediction error [26, 41].”
Continuous depth estimation for multi-view stereo (2009, background): “…the taxonomy of Seitz et al. [22], MVS algorithms can be generally classified into four categories: 3D volumetric approaches [15] [28] [26] [27], surface evolution techniques [21] [8] [31], feature extraction and expansion algorithms [29] [9] [11], and depth map based methods [10] [16] [5] [30].”
Accurate, Dense, and Robust Multi-View Stereopsis (2007, methodology): “Techniques such as space carving[ 12, 15, 19 ]a nd variational methods based on gradient descent [3, 4, 7], level sets [1, 9, 18 ], or graph cuts [3, 8, 17, 22, 23] typically require an initial boundingvolume and/or a wide range of viewpoints.”
Minimizing the Multi-view Stereo Reprojection Error for Triangular Surface Meshes (2008, background): “Also, it does not need complex similarity measures such as normalized cross-correlation or mutual information as [12], is simpler (at least from the implementation point of view), and naturally allows us to deal with significant degradations of some parts of images, as for example can be the case wi”
A Globally Optimal Algorithm for Robust TV-L1 Range Image Integration (2007, methodology): “A commonly used approach is to penalize the surface area of the resulting 3D model, which has been successfully applied in other domains in conjunction with graph-cut algorithms [31] [16] [5] and variational techniques (e.g. [34] [22] [24] [21]).”
Multi-View Stereo via Graph Cuts on the Dual of an Adaptive Tetrahedral Mesh (2007, methodology): “[12] adopt a level set approach that evolves the shape in order to minimize image prediction error.”
Minimizing the Reprojection Error in Surface Reconstruction from Images (2007, methodology): “This can be done once and for all [8, 14, 23] or iteratively, alternating the computation of the visibility with the optimization of the functional [5, 15, 21].”
Multi-View Stereo Revisited (2006, methodology): “…binocular stereo matchers, the best currently available methods employ powerful nonlinear energy minimization methods (e.g., graph cuts [8] [16] [18] [15], level set evolution [3] [13], mesh evolution [7]) often incorporating careful treatment of visibility conditions and silhouette constraints.”
A Variational Method for Scene Flow Estimation from Stereo Sequences (2007, unknown): “[14].”