Ray Markov Random Fields for image-based 3D modeling: Model and efficient inference

By Shubao Liu, David B. Cooper. 2010

36 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

Multi-view Supervision for Single-View Reconstruction via Differentiable Ray Consistency (2017, background): “It is also possible, by jointly modeling appearance and occupancy, to recover 3D structure of objects/scenes from multiple images via ray-potential based optimization [8, 24] or inference in a generative model [13].”
Discrete optimization of ray potentials for semantic 3D reconstruction (2015, background): “A Markov Random Field (MRF) formulation over rays has been proposed to estimate surface geometry and appearance jointly [17, 18].”
Multi-view reconstruction preserving weakly-supported surfaces (2011, methodology): “In [17] they present an approach to multi-view image-based 3D reconstruction by statistically inversing the ray-tracing based image generation process.”
Joint Semantic Segmentation and 3D Reconstruction from Monocular Video (2014, background): “In contrast, the higher order factors used in [23] involve all the voxels starting from the camera.”
A complete statistical inverse ray tracing approach to multi-view stereo (2011, methodology): “The voxel occupancy estimation algorithm in [10] is also reformulated to compute the intermediate terms that are shared with the color estimation algorithm developed later.”
Large-Scale Semantic 3D Reconstruction: An Adaptive Multi-resolution Model for Multi-class Volumetric Labeling (2016, background): “[25] also jointly solve for class label and occupancy state, but model the data term with heuristically shortened ray potentials [32, 36].”
Semantic 3D Reconstruction with Continuous Regularization and Ray Potentials Using a Visibility Consistency Constraint (2016, methodology): “This was formulated in [25, 9, 21, 22, 31] as a problem of finding a voxel labeling in terms of color and occupancy such that the first occupied voxel along a ray has a similar color as the pixel it projects to.”