Multiview Stereo and Silhouette Consistency via Convex Functionals over Convex Domains

By Daniel Cremers, Kalin S. Kolev. 2011

131 citations recorded by the source corpus.

Subfields: Aerospace Engineering, Computer Vision and Pattern Recognition, Geology

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

In Geology

Citations in the corpus

Learning a Multi-View Stereo Machine (2017, neutral): “In the multi-view setting, early work focused on using silhouette information via visual hulls [32], incorporating photo-consistency to deal with concavities (photo hull) [29], and shape reﬁnement using optimization [55, 50, 7, 15].”
Lifting Object Detection Datasets into 3D (2015, background): “…also exists between reconstructing from fewer silhouettes, which may result in a solution with many uncarved voxels, or from a large number of silhouettes which may instead lead to an over-carved or even empty solution, because calibration is not exact and “surrogateness” is only approximate.”
Discrete optimization of ray potentials for semantic 3D reconstruction (2015, methodology): “This constraint has been used in form of a convex relaxation in [6].”
BigBIRD: A large-scale 3D database of object instances (2014, background): “While there exist several 3D vision datasets, most datasets either (1) have few objects, (2) have lowquality objects, (3) provide only single views of objects or scenes, (4) don't contain calibration and pose information, or (5) provide low-resolution RGB data [10], [11], [12], [13], [14], [15].”
Reconstructing PASCAL VOC (2014, methodology): “Similar constraints have been previously used for multiview stereo [9], where they were enforced equally for all Figure 4.”
Large-Scale Semantic 3D Reconstruction: An Adaptive Multi-resolution Model for Multi-class Volumetric Labeling (2016, background): “Many volumetric techniques work with a regular partitioning of the volume of interest [43, 41, 32, 12, 23, 24, 36].”
Generalized Connectivity Constraints for Spatio-temporal 3D Reconstruction (2014, methodology): “Although fine object structures can also be preserved by incorporating exact silhouette information, such as in the work of Cremers and Kolev [6], this method is not applicable if the precomputed silhouettes are not accurate.”
Semantic 3D Reconstruction with Continuous Regularization and Ray Potentials Using a Visibility Consistency Constraint (2016, methodology): “in Sec.3, Eq.13. Together with the regularizer we end up with a surrogate convex but non-smooth program. E (n )(x ;y ;z) = (n ) R (x ;y jx (n );y (n ))+ S (x ;z) (15) s.t. X `2L x ` s =1 8 s; x ` s 2 [0;1] 8 s 2 ; 8 ` 2 L : This energy can be globally minimized using the iterative rst order primal-d”