Multilevel streaming for out-of-core surface reconstruction
By Matthew Bolitho, M. Kazhdan, Randal C. Burns, Hugues Hoppe. 2007
117 citations recorded by the source corpus.
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
- Yasutaka Furukawa
- Konrad Schindler
- Andreas Geiger
- Thomas Brox
- Christoph Vogel
- Luc Van Gool
- Benjamin Ummenhofer
- Jitendra Malik
Citations in the corpus
- Screened poisson surface reconstruction (2013, background): “…of the octree construction, most of the operations involved in the Poisson ACM Transactions on Graphics, Vol. 32, No. 3, Article 29, Publication date: June 2013. reconstruction can be categorized as operations that either accumulate or distribute information [Bolitho et al. 2007, 2009].”
- Global, Dense Multiscale Reconstruction for a Billion Points (2015, methodology): “Both approaches by Fuhrmann and Goesele are local approaches and lack global regularization capabilities. We compare to them in Sect. 8. Sagawa et al. (2005) present a robust method for merging range images with an octree structure.”
- Parallel Poisson Surface Reconstruction (2009, methodology): “To enable the reconstruction of models larger than memory, the algorithm was adapted to operate out-of-core, using a streaming implementation to maintain only a small subset of the data into memory at any given time [ 20 ].”
- Multi-View Stereo: A Tutorial (2015, background): “[115, 41, 116] is another successful and popular meshing software from an oriented point cloud.”
- Rendering Physically Correct Raindrops on Windshields for Robustness Verification of Camera-based Object Recognition (2018, background): “One is to create a mesh representing the surfaces and mapping images as textures onto them [17].”
- Large-Scale Semantic 3D Reconstruction: An Adaptive Multi-resolution Model for Multi-class Volumetric Labeling (2016, methodology): “Contrary to prior work [21, 5, 10], our octree structure is not predetermined by the input data, but refined adaptively, such that we can exploit the per-class probabilities rather than only a minimal energy solution.”