By continuing to browse the site, you are agreeing to our use of cookies. (More details)

PhD: Cultural heritage datasets structuring and smart navigation (M/F)

This offer is available in the following languages:
- Français-- Anglais

Application Deadline : 05 July 2025 00:00:00 Paris time

Ensure that your candidate profile is correct before applying.

General information

Offer title : PhD: Cultural heritage datasets structuring and smart navigation (M/F) (H/F)
Reference : UPR2002-ADEMAN-001
Number of position : 1
Workplace : VILLEURBANNE
Date of publication : 05 June 2025
Type of Contract : FTC PhD student / Offer for thesis
Contract Period : 36 months
Start date of the thesis : 1 October 2025
Proportion of work : Full Time
Remuneration : 2200 gross monthly
Section(s) CN : 07 - Information sciences: processing, integrated hardware-software systems, robots, commands, images, content, interactions, signals and languages

Description of the thesis topic

Title : Cultural heritage datasets structuring and smart navigation : development of a multidimensional and multiscalar information compression approach based on X-LODs

Description :
Cultural heritage data are massive and characterized by their extraordinary diversity and multidimensional nature. These data simultaneously refer to space (3D), time (3D + T) and a wide range of thematic dimensions, creating an exceptionally rich informative framework. This thesis aims to meet the complex challenges raised by the volume and heterogeneity of these documentary corpora, and to significantly improve their exploitation by developing innovative navigation and aggregation methods.

Recent initiatives in heritage and data sciences, such as the work carried out as part of the Notre Dame de Paris scientific action, demonstrate that it is possible to aggregate these data, whether in 3D environments, or as graphs, using methods to identify the diverse relations that link them together (semantic, spatial, temporal, provenance, etc.). However, these visualization methods often lack intelligibility for the end user. Paradoxically, the richer the data representation, the less accessible it seems to be to analysis and understanding. Thus, to navigate in such scenes, we need to find ways of simplifying and compressing the information, to offer navigation modalities that make more sense to users according to their disciplinary profiles and research questions.

The main aim of this thesis is to develop methods for extracting simplified views of the dataset, guided by some degree of dimensional proximity, by representation scale, or by user interests. The methodology includes an in-depth analysis of existing heritage data corpora, the design and implementation of projection and compression algorithms to build levels of detail suited to the various dimensions of heritage data (X-LOD), and the creation of new navigation interfaces exploiting these new approaches.

Required profile and skills :
Engineering degree or Master's degree in computer science.
Curiosity and interest in multidisciplinary work

Work Context

This thesis is part of the 80PRIME TEATIME project “Territoires en Evolution et Analyses Transversales Interdisciplinaires Multi-Echelles”. This project, which involves the LIRIS (Laboratoire d'Informatique en Images et Systèmes d'Information) and MAP (Modèles et Simulations pour l'Architecture et le Patrimoine) laboratories, has received financial support from the CNRS through the MITI interdisciplinary programs. Occasional short-term travels in Marseille are to be expected.

This work will rely on the dataset and digital ecosystem produced as part of the Notre-Dame de Paris scientific action.

PhD Supervisors:
Gilles Gesquière (PR, LIRIS), Livio De Luca (DR, MAP), Violette Abergel (CR, MAP & LIRIS)


--- About the Teatime project ---
The TEATIME project is funded by the 80PRIME program from the CNRS MITI. It targets the study of territories and their transformations at different scales, focusing on the built cultural heritage. Based on the semantic enrichment of spatialized representations, it aims to design mechanisms for better structuring and linking heterogeneous multidimensional datasets combining spatial, temporal and semantic characteristics, as a means of extracting new knowledge. The project's main case study is the Notre-Dame de Paris scientific worksite data corpus.

--- About LIRIS ---
LIRIS (Laboratoire d'InfoRmatique en Image et Systèmes d'information) is a joint research unit (UMR 5205) headed by CNRS, INSA Lyon, Université Claude Bernard Lyon 1, Université Lumière Lyon 2 and École Centrale de Lyon. With over 300 members, it covers a wide range of computer science fields, including artificial intelligence, computer vision, cybersecurity and data science. Its research also extends to the interfaces with human, social and environmental sciences.

--- About MAP ---
The MAP laboratory is a research unit (UPR 2002) of the CNRS Science Humaines & Sociales. Its activities lie at the crossroads of heritage science and data science, and focus on the design and development of digital methods and tools for heritage study and conservation.

The position is located in a sector under the protection of scientific and technical potential (PPST), and therefore requires, in accordance with the regulations, that your arrival is authorized by the competent authority of the MESR.

Constraints and risks

Zone covered by the protection of scientific and technical potential (ZRR):

This position is located in a "restricted zone" as defined in article R.413-5-1 of the French penal code. Access to this area is subject to authorization by the head of the site, in accordance with article 20-4 of decree no. 84-431 of June 6, 1984.