Generalized Connectivity Constraints for Spatio-temporal 3D Reconstruction

By Martin R. Oswald, Jan Stühmer, Daniel Cremers. 2014

45 citations recorded by the source corpus.

Subfields: Aerospace Engineering, 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 Aerospace Engineering

In Computer Graphics and Computer-Aided Design

In Computer Vision and Pattern Recognition

Citations in the corpus

Lifting Object Detection Datasets into 3D (2015, positive): “…the issues of using different object instances as surrogate shapes, this could be combined with other advanced visual hull techniques that explicitly deform the surrogate silhouettes to reduce inconsistencies between the silhouettes [66] or that enforce connectivity of the reconstruction [67].”
Non-Rigid Neural Radiance Fields: Reconstruction and Novel View Synthesis of a Dynamic Scene From Monocular Video (2020, background): “Traditionally, multi-view recordings are required for free viewpoint rendering of dynamic scenes [94, 82, 55].”
Neural Radiance Flow for 4D View Synthesis and Video Processing (2020, unknown): “Most existing works on spatial-temporal 4D reconstruction for general scenes require sufficient observations at each moment [46, 44, 43, 29, 66, 49].”
A Symmetry Prior for Convex Variational 3D Reconstruction (2016, methodology): “…volumetric 3D reconstruction framework which has been used in various settings, e.g. depth map fusion [29], 3D reconstruction [9,27], multi-label semantic reconstruction [5], and spatio-temporal reconstruction [17], with anisotropic regularization [10,5,18] or connectivity constraints [19].”
Structured Prediction of Unobserved Voxels from a Single Depth Image (2016, background): “Additional refinement to respect the observed geometry would likely improve results, but efficient inference is still an open area of research [41].”
Occupancy Flow: 4D Reconstruction by Learning Particle Dynamics (2019, background): “4D Reconstruction: Most works in the area of 4D reconstruction are restricted to a fixed domain by utilizing a template model [2, 5, 15, 27, 30, 63, 75], requiring a multi-view setup [33, 41, 42, 44, 45, 58, 64], or making strong assumptions about the motion e.”
clDice - a Novel Topology-Preserving Loss Function for Tubular Structure Segmentation (2020, methodology): “For non-binary geometries, existing methods applied topology and connectivity constraints onto variational and Markov random field-based methods: tree shape priors for vessel segmentation [44], graph representation priors to natural images [2], higher-order cliques which connect superpixels [53] and”
Topology-Preserving Deep Image Segmentation (2019, methodology): “, connectivity and loop-freeness, have been incorporated into variational [19, 24, 38, 35, 42, 18] and MRF/CRF-based segmentation methods [40, 30, 43, 6, 2, 37, 31, 15].”