Creating Large-Scale City Models from 3D-Point Clouds: A Robust Approach with Hybrid Representation

By Florent Lafarge, Clément Mallet. International Journal of Computer Vision, 2012

371 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Environmental Engineering, Geology

View Paper: https://www.semanticscholar.org/paper/6c0b52e9b12528626f33f08bc236cc3d0878e082

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

1. Andreas Geiger
2. Luc Van Gool
3. Fatma Güney
4. Jitendra Malik
5. Konrad Schindler
6. Ming-Hsuan Yang
7. Joel Janai
8. Aseem Behl

In Environmental Engineering

1. Alexandre Boulch
2. Bertrand Le Saux
3. Nicolas Audebert
4. Hugo Ledoux
5. Uwe Soergel
6. Joachim Niemeyer
7. Fatma Güney
8. Liangliang Nan

In Geology

1. Bertrand Le Saux
2. Nicolas Audebert
3. Alexandre Boulch
4. Hugo Ledoux
5. Uwe Soergel
6. Joachim Niemeyer
7. Liangliang Nan
8. Joel Janai

Citations in the corpus

• Computer Vision for Autonomous Vehicles: Problems, Datasets and State-of-the-Art (2017, methodology): “Early approaches to SLAM have addressed the problem using Bayesian formulations using extended Kalman filters (Smith et al. (1987)) or particle filters (Montemerlo et al. (2002)).”
• FAST SEMANTIC SEGMENTATION OF 3D POINT CLOUDS WITH STRONGLY VARYING DENSITY (2016, background): “It has thus been proposed to fill the remaining gaps with unstructured triangle meshes, generated by triangulating the raw points (Lafarge and Mallet, 2012).”
• Large-Scale Semantic 3D Reconstruction: An Adaptive Multi-resolution Model for Multi-class Volumetric Labeling (2016, methodology): “In this context [30] already used a preceding semantic labeling to improve geometry reconstruction, but not vice versa.”
• Unstructured Point Cloud Semantic Labeling Using Deep Segmentation Networks (2017, methodology): “Hybrid shape extraction were investigated in [LKBH10, LM12] where the surfaces which fit geometric primitives are replaced with the corresponding abstract model while voids remain as triangular mesh.”
• Contextual classification of lidar data and building object detection in urban areas (2014, background): “In an MRF, the class label of an object is statistically dependent on its neighbours, whereas the data of different objects are assumed to be conditionally independent (Li, 2009).”
• State of the art in high density image matching (2014, methodology): “…Goesele et al., 2007; Pollefeys et al., 2008; Snavely et al., 2008; Furukawa et al., 2010; Shan et al., 2013), is presently offering additional automated procedures for both image orientation (Remondino et al., 2012) and 3D reconstruction (Lafarge and Mallet, 2012; Haala, 2013) at different scales.”
• SUM: A Benchmark Dataset of Semantic Urban Meshes (2021, methodology): “To avoid redundant computations of numerous triangles, we first apply mesh over-segmentation (i.e., linear least-squares fitting of planes) based on region growing on the input data to group triangle faces into homogeneous regions [38].”