Postdoc Position on dynamic scene understanding at Istituto Italiano di Tecnologia (IIT - Genova) - [ Postdoc ]

Workplace: Genova, IIT
Added on: 20/11/2018 - Expires on: 01/03/2019

The Visual Geometry and Modelling (VGM, https://vgm.iit.it/) Research Line at Istituto Italiano di Tecnologia (IIT) invites qualified applicants to submit their CV’s for a Postdoc position in Genova, Italy, under the supervision of Dr. Alessio Del Bue.


The VGM mission is to provide computational tools for the large-scale understanding of image and video data for autonomous system for different application domains in engineering, life science and robotics. The scientific core of the VGM Lab relates to the research fields of Computer Vision, Signal Processing and Machine Learning with the primary goal to provide algorithms for:

  • Dynamic 3D scene understanding from video and RGBD data;
  • Reality Capture: 3D reconstruction from images, sound and range data;
  • Large-scale data understanding and modelling for Life Science and Engineering.

Expertise in these research fields applies to several practical and challenging problems in the industry with ongoing collaboration with world-leading companies in machine vision, robotics, automation, energy, avionics, photonics and fashion industries.


VGM is opening a postdoc position to work on dynamic 3D scene understanding with topics related to semantic simultaneous localisation and mapping (S-SLAM) and semantic structure from motion (S-SfM) which are core research themes of the Lab (Crocco et al., CVPR 2016), (Magerand & Del Bue, ICCV2017), (Rubino et al., PAMI 2018). As these previous works mainly deal with static scenes, the VGM lab will push forward these activities developing computational methods for geometric and semantic understanding in challenging dynamic and non-rigid environments. The key aspect of the research carried at VGM will focus on the fusion of state of the art deep architectures with 3D reasoning from multi-view images or RGBD data.

Required qualifications:

  • A Ph.D. in computer science or related field (with specialization in either computer vision, information retrieval or machine learning);
  • Proficiency with programming languages, in particular Python, C/C++ and MATLAB;
  • Experience on SLAM and multi-view geometry approaches for sparse and dense 3D reconstruction;
  • Publication in major Computer Vision conferences/journals (e.g. CVPR, ICCV, ECCV, TPAMI, IJCV, IVC, CVIU);
  • Good communication skills and ability to cooperate;
  • Proficient in English language (written and oral).

Desirable skills:

  • Practical experience on Deep Learning algorithms and relevant platforms for geometric learning (e.g. TensorFlow, PyTorch, etc.);
  • Knowledge of OpenCV, PCL and Open3D libraries;
  • Experience of graph structure applications e.g. scene graph estimation, matching, retrieval or inference;

The salary offered to the successful candidate will be commensurate to experience and skills.

The call will remain open until the position is filled but a first deadline for evaluation of candidates will be March 1, 2019. Please send your application to pavis@iit.it and applications@iit.it quoting “BC 76193 - VGM Postdoc Position on dynamic scene understanding” in the e-mail subject. Your application shall contain a detailed CV, a one-page research statement and contact information of two referees.

Fondazione Istituto Italiano di Tecnologia (http://www.iit.it) is a non-profit institution created with the objective of promoting technological development and higher education in science and technology. Research at IIT is carried out in highly innovative scientific fields with state-of-the-art technology.
Istituto Italiano di Tecnologia is an equal opportunity employer that actively seeks diversity in the workforce.

Please note that the data that you provide will be used exclusively for the purpose of professional profiles’ evaluation and selection, and in order to meet the requirements of Istituto Italiano di Tecnologia.

Istituto Italiano di Tecnologia, based in Genoa, Via Morego 30, will process your data acting as Data Controller, in compliance with the rules on protection of personal data, including those related to data security.

Please also note that, pursuant to articles 15 et. seq. of European Regulation no. 679/2016 (General Data Protection Regulation), you may exercise your rights at any time by contacting the Data Protection Officer (phone +39 010 71781 - email: dpo[at]iit.it)

Contacts

applications@iit.it
Pavis
pavis@iit.it
Involved Research lines
Visual Geometry and Modelling

INFORMATION NOTICE ON COOKIES

IIT's website uses the following types of cookies: browsing/session, analytics, functional and third party cookies. Users can choose whether or not to accept the use of cookies and access the website. By clicking on "Further Information", the full information notice on the types of cookies will be displayed and you will be able to choose whether or not to accept them whilst browsing on the website
Further Information
Accept and close