Fusion of depth maps with multiple scales
By Simon Fuhrmann, Michael Goesele. 2011
120 citations recorded by the source corpus.
Subfields: 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 Computer Graphics and Computer-Aided Design
- Marc Pollefeys
- Maxim Tatarchenko
- Andreas Geiger
- Carlos Hernández
- Thomas Brox
- Alexey Dosovitskiy
- Daniel Cremers
- Lubor Ladicky
In Computer Vision and Pattern Recognition
- Luc Van Gool
- Jitendra Malik
- Vladlen Koltun
- Andreas Geiger
- Dacheng Tao
- Ming-Hsuan Yang
- Andrea Vedaldi
- Cordelia Schmid
Citations in the corpus
- Octree Generating Networks: Efficient Convolutional Architectures for High-resolution 3D Outputs (2017, background): “Octrees have a long history in classical 3D reconstruction and depth map fusion [21, 1, 11, 34, 6, 31].”
- From Point Clouds to Mesh Using Regression (2017, background): “To overcome this problem, Fuhrmann et al. [10] propose a fusion algorithm that copes with depth maps of varying resolutions, allowing to simultaneously represent low resolution regions as well as high resolution details.”
- Volumetric 3D mapping in real-time on a CPU (2014, background): “Fuhrmann et al. [8] proposed to store data not only at the leaves but at all levels of the tree.”
- Large-Scale Multi-resolution Surface Reconstruction from RGB-D Sequences (2013, methodology): “Various methods have been proposed to overcome this limitation, for example, by using rolling reconstruction volumes [14, 19] or octree data structures [7, 21].”
- Global, Dense Multiscale Reconstruction for a Billion Points (2015, methodology): “To avoid artifacts due to different point resolutions, Fuhrmann and Goesele [5] propose a fusion method that averages samples from depth maps at compatible scales within an octree data structure.”
- A Survey of Surface Reconstruction from Point Clouds (2017, unknown): “…general implicitfield SigningtheUnsigned[MDGD ∗ 10] general implicitfield ConeCarving[SSZCO10] general implicitfield Multi-ScaleScanMerge[FG11] general implicitfield Volumetricsmoothness ROSA[TZCO09] organic skeletoncurve ArterialSnakes[LLZM10] man-made skeletoncurve VASE[TOZ ∗ 11]…”
- Multi-View Stereo: A Tutorial (2015, background): “Even after the alignment, it is not a trivial task to reconstruct a single consistent 3D model that is as large as an entire city and contains details as small as individual objects in every store front [69, 65, 66].”