In this project we investigate 3D computer vision methods of recognition, reconstruction etc. in large scale. That is, methods are used in domains that contain a lot of 3D and 2D data. Such environments are, for example, 2D and 3D maps with street view images.

The project is done in collaboration with our industrial partners.


Junsheng Fu E-mail Research Student
Pouria Babahajiani E-mail Research Student
Dr. Lixin Fan E-mail Principal Scientist
Dr. Arto Lehtiniemi E-mail
Joni Kamarainen E-mail Professor

Selected Publications

Indoor Objects and Outdoor Urban Scenes Recognition by 3D Visual Primitives

By J. Fu and J.-K. Kamarainen and A. Glent Buch and N. Krueger In Asian Conf. on Computer Vision (ACCV) Workshop on Big Data in 3D Computer Vision 2014.

Our method can be used to learn a 3D object model from a single (stereo or RGB-D) view, store the model to the database and then match novel views to the database objects.

Download: PDF, BibTex

A 3D Map Augmented Photo Gallery Application on Mobile Device

By J. Fu and L. Fan and K. Roimela and Y. You and V. Mattila In 21st Int. Conf. on Image Processing (ICIP2014) 2014.

Download: PDF, BibTex


Data sets

Authors and teams