High Accuracy and Visibility-Consistent Dense Multiview Stereo

By Hoang-Hiep Vu, Patrick Labatut, Jean-Philippe Pons, Renaud Keriven. 2012

293 citations recorded by the source corpus.

Subfields: 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 Computer Vision and Pattern Recognition

In 3D Vision & Pose

Citations in the corpus

3D Instance Segmentation of MVS Buildings (2021, methodology): “Multi-view images are captured by Unmanned Aerial Vehicle (UAV) and used to automatically reconstruct dense 3D mesh models of large urban scenes [1], [2].”
Discrete optimization of ray potentials for semantic 3D reconstruction (2015, neutral): “[27] uses a thetrahedronization of the space.”
State of the art in high density image matching (2014, methodology): “The image-matching problem is nowadays solved using stereopairs ( stereomatching ) (Hirschm € uller, 2008; Gehrig et al., 2009; Tola et al., 2010; Haala and Rothermel, 2012; Hermann and Klette, 2013) or via identi ﬁ cation of correspondences in multiple images ( multi-view stereo – MVS) (Collins, 19”
Towards Probabilistic Volumetric Reconstruction Using Ray Potentials (2015, background): “More recently, researchers have shifted their focus from reconstructing isolated single objects to more challenging general scenes that involve significant occlusions, textureless or reflective surfaces, transient objects, varying illumination conditions, and camera mis-registration errors [7, 16, 1”
Tanks and temples (2017, methodology): “This benchmark provided a significant challenge and supported the development and validation of advanced reconstruction pipelines [Langguth et al. 2016; Schönberger et al. 2016; Tola et al. 2012; Vu et al. 2012].”
MVSNet: Depth Inference for Unstructured Multi-view Stereo (2018, background): “It is reported in recent MVS benchmarks [2,3] that, although current state-of-the-art algorithms [4,5,6,7] perform very well on the accuracy, the reconstruction completeness still has large room for improvement.”
Multi-View Mesh Reconstruction with Neural Deferred Shading (2022, unknown): “[2, 6, 18, 19, 26, 68, 72, 74].”
Semantic 3D Reconstruction with Continuous Regularization and Ray Potentials Using a Visibility Consistency Constraint (2016, background): “Using a discrete graph formulation [16, 33] propose to model the free space between the camera center and the measured depth with pairwise potentials.”
Photometric Bundle Adjustment for Dense Multi-view 3D Modeling (2014, methodology): “The discrete gradient descent flow allows vertices to be moved at their correct location and to preserve surface edges (as in [2, 23]).”