3D Reconstruction of Urban Scenes from Street-side and Airborne Imagery
András Bódis-Szomorú
Ph.D. Dissertation ETH Zurich 2018
Defended in Dec 2017
Accepted on the recommendation of
Prof. Dr. Luc Van Gool, Prof. Dr. Konrad Schindler and Dr. Florent Lafarge
Overview
3D models produced from this work have received media coverage. You can read about the following 3D computer vision / geometry processing topics in my thesis.
![sparse3dscan_400px sparse3dscan_400px](http://andras.szomoru.com/wp-content/uploads/elementor/thumbs/sparse3dscan_400px-q8ogr1jjk2oak0n1lfy70759qah1yp6bb730h651c0.jpg)
Real-time 3D point cloud reconstruction from video at 25 fps on CPU for mobile mapping.
![huns_400px huns_400px](http://andras.szomoru.com/wp-content/uploads/elementor/thumbs/huns_400px-q8ogqyq0zkkfl6r51wqbapuvy4uyblv4at4k1c97uo.jpg)
Hierarchical Unregularized Superpixel (HUNS) algorithm outperforming methods like SLIC, ERS or SEEDS.
![sfmplanes_400px sfmplanes_400px](http://andras.szomoru.com/wp-content/uploads/elementor/thumbs/sfmplanes_400px-q8ogr1jjk2oak0n1lfy70759qah1yp6bb730h651c0.jpg)
Image-based modelling by combining sparse 3D points and multi-view plane segmentation over superpixels.
![spmesh_400px spmesh_400px](http://andras.szomoru.com/wp-content/uploads/elementor/thumbs/spmesh_400px-q8ogqyq0zkkfl6r51wqbapuvy4uyblv4at4k1c97uo.jpg)
Compact surface mesh reconstruction from images via sparse 3D points and vertex depth optimization.
![spdem_400px spdem_400px](http://andras.szomoru.com/wp-content/uploads/elementor/thumbs/spdem_400px-q8ogqyq0zkkfl6r51wqbapuvy4uyblv4at4k1c97uo.jpg)
Efficient conversion of dense height or depth maps into a compact mesh via fast piecewise-planar partitioning.
![fusion_400px fusion_400px](http://andras.szomoru.com/wp-content/uploads/elementor/thumbs/fusion_400px-q8ogr0lpd8n08eoeqxjkfpdt4wlor02kz2fizw6fi8.jpg)
Efficient surface reconstruction fusing street-side and point clouds via ray shooting into a tetrahedralization.
![airborne_semantic_400px airborne_semantic_400px](http://andras.szomoru.com/wp-content/uploads/elementor/thumbs/airborne_semantic_400px-q8ogr0lpd8n08eoeqxjkfpdt4wlor02kz2fizw6fi8.jpg)
Segmentation of airborne 3D models into buildings, vegetation, ground, water in spite of geometric defects.
![texturing_400px texturing_400px](http://andras.szomoru.com/wp-content/uploads/elementor/thumbs/texturing_400px-q8ogqyq0zkkfl6r51wqbapuvy4uyblv4at4k1c97uo.jpg)
Fast multi-view texturing of urban surface models jointly from airborne and street-side data.
![facade_semantic_400px facade_semantic_400px](http://andras.szomoru.com/wp-content/uploads/elementor/thumbs/facade_semantic_400px-q8ogr0lpd8n08eoeqxjkfpdt4wlor02kz2fizw6fi8.jpg)
Image-based facade mesh segmentation into semantic parts and ways to reduce computational burden.
BibTeX
@phdthesis{BodisPhdThesis2018,
author = {András Bódis-Szomorú},
title = {3D Reconstruction of Urban Scenes from Street-Side and Airborne Imagery},
publisher = {ETH Zurich},
school = {ETH Zurich}
year = {2018},
language = {en},
size = {262 p.},
DOI = {10.3929/ethz-b-000286410},
keywords = {Multi-view reconstruction; Structure-from-Motion; Computer Vision; Superpixels; Surface Mesh; Image-based modelling; Semantic Segmentation; Urban modelling; Volumetric reconstruction; Multi-view texturing; Multi-view stereo; Image Processing; Airborne photogrammetry; Mobile mapping},
}