PamiTC/CVPR Job Board - Posting Details

Title: PhD on Large Scale Semantic 3D Reconstruction of CitiesPosted: February 24, 2014
Company/Institution: Ecole des Ponts ParisTech (Universite Paris-Est)
Location: Paris, France
Department: Computer Science and Applied Mathematics department


Ecole des Ponts ParisTech at Universite Paris-Est has a new opening for a PhD scholarship in the areas of computer vision and machine learning (in the computer science and applied mathematics department).

The topic of the PhD will be related to large scale semantic 3D reconstruction of cities, where the overall goal will be to develop advanced large-scale image analysis and learning techniques to semantize city images and produce semantized 3D reconstructions of large-scale urban environments. Geometric 3D models of existing cities have a wide range of applications, such as navigation in virtual environments and realistic sceneries for video games and movies. A number of players (Google, Microsoft, Apple) have started to produce such data. However, the models feature only plain surfaces, textured from available pictures. This limits their use in urban studies and in the construction industry, excluding in practice applications to diagnosis and simulation.

Here we wish to go beyond that by producing semantized 3D models, i.e., models which are not bare surfaces but which identify architectural elements such as windows, walls, roofs, doors, etc. To achieve this goal, novel large-scale machine learning algorithms will be developed to recognize various types of architectural elements and styles in input images. These methods will be able to fully exploit very large amounts of data of various modalities (including large-scale panoramas, terrestrial and aerial images, cadastral maps, LIDAR data) while at the same time requiring a minimum amount of user annotation (weakly supervised learning). Some methods will also cover the automatic discovery of recurring elements in building images (mostly unsupervised learning) to enrich image correlation and inferred information.

We are searching for outstanding and highly motivated students with

  • an excellent degree (M.Sc., M.Eng. or equivalent) in Computer Science, Mathematics, or a related field (e.g. Electrical Engineering)
  • demonstrable interest in computer vision and machine learning,
  • strong mathematical understanding, and
  • very good programming skills.

Any prior publications in first-tier computer vision/machine learning journals (TPAMI, IJCV, JMLR) and conferences (CVPR, ICCV, ECCV, ICML, NIPS) would also be a very important plus.

Successful applicants will join an expanding research group consisting of more than 25 faculty members seeking scientific excellence in the area of learning and visual computing, and will be submerged into an "interdisciplinary" environment with over 75 permanent research scientists.

Deadline for applications: Open until filled

The position is associated with a full PhD scholarship that offers, on top of PhD allowance, full health and retirement benefits.

Application Instructions:

The application package consists of a motivation letter, full CV, names and contact details of two references, transcript of grades from under-graduate and graduate program, and a link to a Masters thesis (as well as to any relevant publications).

Applications should be submitted via electronic mail directly to Prof. Nikos Komodakis (