Patches, Planes and Probabilities: A Non-Local Prior for Volumetric 3D Reconstruction

By Ali O. Ulusoy, Michael J. Black, Andreas Geiger. 2016

33 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

1. Andreas Geiger
2. Yiyi Liao
3. Ali O. Ulusoy
4. Michael J. Black
5. Simon Donné
6. Luc Van Gool
7. Horst Bischof
8. Gernot Riegler

In Computer Graphics and Computer-Aided Design

1. Andreas Geiger
2. Yiyi Liao
3. Michael J. Black
4. Ali O. Ulusoy
5. Simon Donné
6. Gernot Riegler
7. Horst Bischof
8. Luc Van Gool

In Computer Vision and Pattern Recognition

1. Andreas Geiger
2. Luc Van Gool
3. Ming-Hsuan Yang
4. Jitendra Malik
5. Xiaogang Wang
6. Dacheng Tao
7. Andrea Vedaldi
8. Andrew Zisserman

Citations in the corpus

• RayNet: Learning Volumetric 3D Reconstruction with Ray Potentials (2018, background): “To address this limitation, a number of approaches have phrased 3D reconstruction as inference in a Markov random field (MRF) by exploiting the special characteristics of high-order ray potentials [19, 28, 33, 35].”
• OctNetFusion: Learning Depth Fusion from Data (2017, methodology): “Instead, they rely on simple hand-crafted priors such as spatial smoothness [26], or piecewise planarity [47].”
• Deep Marching Cubes: Learning Explicit Surface Representations (2018, methodology): “Towards this goal, many existing approaches formulate 3D reconstruction as inference in a Markov random field [2, 21, 41, 46] or as a variational problem [17, 47].”
• Semantic Multi-view Stereo: Jointly Estimating Objects and Voxels (2017, methodology): “The results indicate that both the proposed object shape prior and the planarity prior [33] improve reconstruction accuracy over the baseline with no prior [34].”