A quasi-dense approach to surface reconstruction from uncalibrated images

By Maxime Lhuillier, Long Quan. 2005

509 citations recorded by the source corpus.

Subfields: Aerospace Engineering, Computational Mechanics, 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 Aerospace Engineering

In Computational Mechanics

In Computer Vision and Pattern Recognition

Citations in the corpus

3D-R2N2: A Unified Approach for Single and Multi-view 3D Object Reconstruction (2016, neutral): “Apr 2016 2 C. B. Choy, D. Xu, J. Gwak, K. Chen, and S. Savarese These restrictions stem from a number of key technical assumptions. One typical assumption is that features can be matched across views [3,4,5,6] as hypothesized by the majority of the methods based on SFM or SLAM [7,8]. It has been dem”
Point-Based Multi-View Stereo Network (2019, unknown): “Traditional methods [17, 5, 18] generate dense 3D patches by expanding from confident matching key-points repeatedly, which is potentially time-consuming.”
Cascade Cost Volume for High-Resolution Multi-View Stereo and Stereo Matching (2019, methodology): “Multi-View Stereo According to the comprehensive survey [5], works in traditional muti-view stereo can be roughly categorised into volumetric methods [13, 14, 18, 33], which estimate the relationship between each voxel and surfaces; point cloud based methods [6, 19], which directly process 3D points”
Structure from motion photogrammetry in physical geography (2016, methodology): “…methods where individual depth maps (showing the distance between the camera viewpoint to the 3D scene objects) are combined into a single model, e.g. Li et al. (2010a); and (iv) Patch-based methods where collections of small patches or surfels represent the scene, e.g. Lhuillier and Quan (2005).”
Accurate, Dense, and Robust Multiview Stereopsis (2010, methodology): “2) Expansion: A technique similar to [17], [18], [22], [23], [24] is used to spread the initial matches to nearby pixels and obtain a dense set of patches.”
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].”
Recurrent MVSNet for High-Resolution Multi-View Stereo Depth Inference (2019, unknown): “They either apply local depth propagation [19, 9, 10, 24] to iteratively refine depth maps/point clouds, or sequentially regularize the cost volume using simple plane sweeping [7] and 2D spatial cost aggregation with depth-wise winner-take-all [28, 31].”
Multi-View Stereo via Graph Cuts on the Dual of an Adaptive Tetrahedral Mesh (2007, background): “Lhuillier and Quan [10] detect a quasi-dense set of reliable 3D points and reconstruct the surface within a variational framework.”
Deep Stereo Using Adaptive Thin Volume Representation With Uncertainty Awareness (2019, background): “Researchers have also tried to reconstruct point clouds [22, 13, 35, 52, 36, 2], however the high dimensionality of a point cloud often results in noisy outliers since a point cloud does not efficiently encode connectivity between points.”
The structure-from-motion reconstruction pipeline - a survey with focus on short image sequences (2010, background): “publications these systems and their improvements are covered [3, 14, 15, 21, 22, 23, 30, 33, 34, 38, 42, 46].”
PGSR: Planar-Based Gaussian Splatting for Efficient and High-Fidelity Surface Reconstruction (2024, unknown): “Traditional methods adhere to the universal multi-view stereo pipeline, whichcanberoughlycategorizedbasedontheinterme-diate representation they rely on, such as point cloud [31], [32], volume [33], depth map [34], [35], [36], etc.”
Accurate, Dense, and Robust Multi-View Stereopsis (2007, methodology): “Quantitative evaluations provided at [1] show that the proposed approach outperforms all the other evaluated techniques both in terms of accuracy and completeness for four out of the six datasets.”
Multi-View Stereo: A Tutorial (2015, unknown): “In the MVS context, Lhuillier and Quan proposed an early work, where patches are expanded in a greedy fashion [132].”
Real Time Localization and 3D Reconstruction (2006, background): “It is still today a very active field of research, and several successful systems currently exist [13] [1] [12] [9] [15].”
A Surface-Growing Approach to Multi-View Stereo Reconstruction (2007, methodology): “The method in [13] employs a level-set evolution approach to compute a surface based on the triangulated quasi-dense point correspondences, image silhouettes, and photo-consistency measures.”
MVSNet: Depth Inference for Unstructured Multi-view Stereo (2018, methodology): “Point cloud based methods operate directly on 3D points, usually relying on the propagation strategy to gradually densify the reconstruction [23,4].”