Projects

Neural 3D Reconstruction

Instant Neural Radiance Fields (Instant NeRFs)

Thomas Müller, Alex Evans, Isaac Deutsch, András Bódis-Szomorú, Michael Shelley, Christoph Schied, Marco Foco, Alexander Keller (NVIDIA), SIGGRAPH Real-Time Live! Demo, 2022

Image-based 3D Urban Modelling

3D Reconstruction of Urban Scenes from Street-side and Airborne Imagery

András Bódis-Szomorú, Ph.D. Dissertation, ETH Zurich, 2018
Referees: Prof. Luc Van Gool, Prof. Konrad Schindler, Dr. Florent Lafarge

Efficient Volumetric Fusion of Airborne and Street-Side Data for Urban Reconstruction

András Bódis-Szomorú, Hayko Riemenschneider, Luc Van Gool, International Conference on Pattern Recognition (ICPR) 2016 (Finalist for the Best Industry-Related Paper Award)

Efficient Edge-Aware Surface Mesh Reconstruction for Urban Scenes

András Bódis-Szomorú, Hayko Riemenschneider, Luc Van Gool, Computer Vision and Image Understanding (CVIU), 157(C), 3-24, April 2017

Superpixel Meshes for Fast Edge-Preserving Surface Reconstruction

András Bódis-Szomorú, Hayko Riemenschneider, Luc Van Gool, IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Boston, MA, USA, 7-12 June 2015

Fast, Approximate Piecewise-Planar Modeling Based on Sparse Structure-from-Motion and Superpixels

András Bódis-Szomorú, Hayko Riemenschneider, Luc Van Gool, IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Columbus, Ohio, 24-27 June 2014

Learning Where To Classify In Multi-View Semantic Segmentation

Hayko Riemenschneider, András Bódis-Szomorú, Julien Weissenberg, Luc Van Gool, European Conference on Computer Vision (ECCV), Zurich, Switzerland, 6-12 September 2014

Efficient Architectural Structural Element Decomposition

Nikolay Kobyshev, Hayko Riemenschneider, András Bódis-Szomorú, Luc Van Gool, Computer Vision and Image Understanding (CVIU), 157(C), 300-312, April 2017

Architectural Decomposition for 3D Landmark Building Understanding

Nikolay Kobyshev, Hayko Riemenschneider, András Bódis-Szomorú, Luc Van Gool, IEEE Winter Conference on Applications of Computer Vision (WACV), Lake Placid, NY, USA, 7-9 March 2016

3D Saliency for Finding Landmark Buildings

Nikolay Kobyshev, Hayko Riemenschneider, András Bódis-Szomorú, Luc Van Gool, International Conference on 3D Vision (3DV), Stanford University, California, USA, 25-28 Oct 2016

Autonomous Driving

Optimization methods to calibrate a stereo rig with increased accuracy for vehicular applications

András Bódis-Szomorú, Tamás Dabóczi, IEEE Instrumentation and Measurement Technology Conference (I2MTC) 2012, Graz, Austria, 13-16 May 2012 (Best  Paper Award)

A Lane Detection Algorithm based on Wide-Baseline Stereovision for Advanced Driver Assistance

András Bódis-Szomorú, Tamás Dabóczi, Zoltán Fazekas, 7th Conference of the Hungarian Association for Image Processing and Pattern Recognition (KÉPAF) 2009, Budapest, Hungary, 28-30 Jan 2009

A Stereo Vision System For Lane Detection and Tracking (in Hungarian)

András Bódis-Szomorú, Bálint Virágh, István Wahl, Zoltán Fazekas, Tamás Dabóczi, Future Vehicle – Automotive Innovation (A Jövő Járműve – Járműipari Innováció) Vol. II., No. 3-4, pp. 44-55, 2008

Calibration and Sensitivity Analysis of a Stereo Vision-Based Driver Assistance System

András Bódis-Szomorú, Tamás Dabóczi, Zoltán Fazekas, Book Chapter in Stereo Vision, InTech Open Access, Nov 2008 [Preprint pdf] [InTechOpen book]

Camera Calibration and Pose Estimation using Planar Features and Sensitivity Analysis

András Bódis-Szomorú, IEEE Proceedings of the 15th PhD Mini-Symposium, Budapest, Hungary, 4-5 Feb 2008

A Far-Range Off-line Camera Calibration Method for Stereo Lane Detection Systems

András Bódis-Szomorú, Tamás Dabóczi, Alexandros Soumelidis, Zoltán Fazekas, IEEE Instrumentation and Measurement Technology Conference (IMTC), Warsaw, Poland, 1-3 May 2007

Cornea Reconstruction

Specular Surface Reconstruction Method for Multi-Camera Corneal Topographer Arrangements

Zoltán Fazekas, Alexandros Soumelidis, András Bódis-Szomorú, Ferenc Schipp, Béla Csákány, János Németh, Book Chapter In: Recent Advances in Biomedical Engineering, InTech Open, Oct 2009

Surface Reconstruction Method for Multi-View Corneal Tomography

Zoltán Fazekas, Alexandros Soumelidis, András Bódis-Szomorú, Ferenc Schipp, Béla Csákány, János Németh, 7th Conference of the Hungarian Association for Image Processing and Pattern Recognition (KÉPAF) 2009

Specular Surface Reconstruction for Multi-Camera Corneal Topographer Arrangements

Zoltán Fazekas, Alexandros Soumelidis, András Bódis-Szomorú, Ferenc Schipp, Int’l Conf of the IEEE Engineering in Medicine and Biology Society (EMBC), Vancouver, British Columbia, Canada, 20-25 Aug 2008

Embedded Computing Solutions Used in a Multicamera Corneal Topographer

Alexandros Soumelidis, Zoltán Fazekas, Ferenc Schipp, Zsolt Lichtenberger, András Bódis-Szomorú, Regional Conference on Embedded and Ambient Systems (RCEAS) 2007, Budapest, Hungary, 22-24. Nov 2007

Other topics

Class-Specific Object Pose Estimation and Reconstruction Using 3D Part Geometry

Arun CS Kumar, András Bódis-Szomorú, Suchendra Bhandarkar, Mukta Prasad, European Conference on Computer Vision (ECCV) 2016 Workshop on Geometry Meets Deep Learning, Amsterdam, the Netherlands, 9 Oct 2016

High-precision ground-truth data for evaluating dense stereo and optical flow algorithms

András Bódis-Szomorú, Tamás Dabóczi, 8th Conference of the Hungarian Association for Image Processing and Pattern Recognition (KÉPAF), Szeged, Hungary, 25-28 Jan 2011

Design and Implementation of a Motor Control Unit for a Mobile Robot

András Bódis-Szomorú, Master Thesis in Hungarian, Budapest University of Technology and Economics, 2005
Supervisor: Dr. Tamás Dabóczi

Nonparametric Identification and Signal Reconstruction as two Consecutive Deconvolution Steps

Tamás Dabóczi, András Bódis-Szomorú, IEEE Instrumentation & Measurement Technology Conference (IMTC), Ottawa, ON, Canada, 16-19 May 2005

Passive Electro-Magnetic Interference Filter for Electric Power Assisted Steering

András Bódis-Szomorú, ElektroNet, 14(8):25-29, Dec 2005 (No. 2005.8)