Silhouette and stereo fusion for 3D object modeling

By Carlos Hernández Esteban, Francis J. M. Schmitt. 2003

551 citations recorded by the source corpus.

Subfields: Aerospace Engineering, Computer Graphics and Computer-Aided Design, Computer Vision and Pattern Recognition, 3D Vision & Pose

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 Graphics and Computer-Aided Design

In Computer Vision and Pattern Recognition

In 3D Vision & Pose

Citations in the corpus

Category-specific object reconstruction from a single image (2014, methodology): “We follow the suggestion of [14] and initialize our mean shape with a soft visual hull computed using all training instances.”
Using Multiple Hypotheses to Improve Depth-Maps for Multi-View Stereo (2008, methodology): “The second group make use of some form of global optimisation strategy on a volumetric representation to extract a surface [5, 14, 6, 12, 7].”
Deep Volumetric Video From Very Sparse Multi-view Performance Capture (2018, methodology): “Visual hulls created from multi-view silhouette images are widely used for multi-view reconstruction, [6, 11–14, 10, 15], since they are fast and easy to compute and well approximate the underlying 3D geometry.”
High Accuracy and Visibility-Consistent Dense Multiview Stereo (2012, unknown): “The benefits of this approach have long been recognized in mesh processing, but have seldom been demonstrated in computer vision [11], [26], [52].”
Towards Internet-scale multi-view stereo (2010, methodology): “Many of the best performing MVS algorithms instead reconstruct a global 3D model directly from the input images [9, 13, 20, 24].”
Point-Based Multi-View Stereo Network (2019, background): “A number of 3D representations are adopted, including volumes [26, 9], deformation models [3, 31], and patches [5], which are iteratively updated through multi-view photometric consistency and regularization optimization.”
Categorizing object-action relations from semantic scene graphs (2010, background): “In cognitive vision, many new approaches for object recognition from 3D models have been introduced [5], [6], [7].”
A Surface Deformation Framework for 3D Shape Recovery (2006, background): “The external force component, Fext, is based on silhouette information, though it is also possible to incorporate texture or color consistency information [21].”
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].”
Multi-View Stereo via Graph Cuts on the Dual of an Adaptive Tetrahedral Mesh (2007, methodology): “We opt for a robust approach under which we select the best subset of cameras for each point as in [4].”
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].”
Neural 3D Video Synthesis from Multi-view Video (2021, unknown): “Multi-view stereo [15, 50] and visual hull reconstructions [13, 28] have been successfully employed.”
Generalized Connectivity Constraints for Spatio-temporal 3D Reconstruction (2014, methodology): “(2) The delta function δ in combination with d max i = arg max d C i (x, d) performs a ray-based denoising of these measures and represents the voting scheme proposed by Hernández and Schmitt [9] and μ is a scaling parameter.”
Accurate, Dense, and Robust Multiview Stereopsis (2010, background): “Algorithms based on deformable polygonal meshes [10], [11], [12] demand a good starting point —for example, a visual hull model [13]—to initialize the corresponding optimization process, which limits their applicability.”
Multi-View Stereo Reconstruction and Scene Flow Estimation with a Global Image-Based Matching Score (2007, methodology): “The matching measure at a point relies on a local approximation of the surface, either by a fronto-parallel plane [20, 12] or at best by the tangent plane [8, 13, 6, 9].”
PIFu: Pixel-Aligned Implicit Function for High-Resolution Clothed Human Digitization (2019, background): “Early attempts are based on visual hulls [37, 61, 15, 14] which uses silhouettes from multiple views to carve out the visible areas of a capture volume.”
Efficient Multi-View Reconstruction of Large-Scale Scenes using Interest Points, Delaunay Triangulation and Graph Cuts (2007, background): “Large-scale cluttered scenes for which no reliable initial guess of geometry is available also disqualify the deformable model framework [11, 13, 12, 21, 28, 32].”