Project description
Advancing camera motion estimation and VPR technology
Camera motion can be analysed with millimetre-level accuracy using local image features. However, this efficiency declines in real-world situations due to changes in viewpoint, dynamic scene elements and variable lighting or weather conditions. Visual place recognition (VPR) is robust against appearance changes but is limited to coarse geometric models. Supported by the Marie Skłodowska-Curie Actions programme, the PAVPR project will overcome the current limitations of VPR and advance VPR and camera motion estimation to the next level. The project will use 3D modelling within VPR embeddings and develop novel mapping and localisation methods, enabling both accurate motion estimation and robustness to appearance changes.
Objective
Camera motion can be estimated from images with millimeter-level accuracy through local features, but only in carefully controlled data. In real-world conditions, performance often deteriorates under moderate illumination or viewpoint changes, dynamic scene elements or weather conditions. By contrast, Visual Place Recognition (VPR) exhibits strong robustness to visual appearance changes, yet remains limited to coarse geometric models, as it encodes image similarities without explicitly exploiting 3D information.
The goal of our Pose-Aware Visual Place Recognition (PAVPR) is to advance VPR and camera motion estimation by integrating explicit 3D modeling in VPR embeddings, thereby combining robustness to appearance changes with accurate motion estimation. Building on this foundation, PAVPR will also develop localization and mapping methods that rely on holistic image descriptors rather than traditional local feature-based pipelines. This approach offers several advantages, including improved resilience to visual variations, stronger privacy guarantees, and reduced computational costs. Finally, PAVPR will design novel benchmarks that account for the geometric proportionality of VPR embeddings, addressing a key limitation of current datasets and recall-based evaluations. The project also includes a secondment at VANDAL (Politecnico di Torino), enabling further collaboration with leading VPR experts and fostering deeper insights into the proposed research tasks.
Overall, this work aligns with the EU Work Programme on trustworthy, safe, and resilient AI and robotics systems. By enhancing both the efficiency and robustness of localization technologies, PAVPR will strengthen Europe’s leadership in trustworthy AI and deliver significant impact to the scientific community and industrial stakeholders alike.
Fields of science (EuroSciVoc)
CORDIS classifies projects with EuroSciVoc, a multilingual taxonomy of fields of science, through a semi-automatic process based on NLP techniques. See: The European Science Vocabulary.
CORDIS classifies projects with EuroSciVoc, a multilingual taxonomy of fields of science, through a semi-automatic process based on NLP techniques. See: The European Science Vocabulary.
- engineering and technology electrical engineering, electronic engineering, information engineering electronic engineering sensors optical sensors
- engineering and technology electrical engineering, electronic engineering, information engineering electronic engineering robotics
You need to log in or register to use this function
Keywords
Project’s keywords as indicated by the project coordinator. Not to be confused with the EuroSciVoc taxonomy (Fields of science)
Project’s keywords as indicated by the project coordinator. Not to be confused with the EuroSciVoc taxonomy (Fields of science)
Programme(s)
Multi-annual funding programmes that define the EU’s priorities for research and innovation.
Multi-annual funding programmes that define the EU’s priorities for research and innovation.
-
HORIZON.1.2 - Marie Skłodowska-Curie Actions (MSCA)
MAIN PROGRAMME
See all projects funded under this programme
Topic(s)
Calls for proposals are divided into topics. A topic defines a specific subject or area for which applicants can submit proposals. The description of a topic comprises its specific scope and the expected impact of the funded project.
Calls for proposals are divided into topics. A topic defines a specific subject or area for which applicants can submit proposals. The description of a topic comprises its specific scope and the expected impact of the funded project.
Funding Scheme
Funding scheme (or “Type of Action”) inside a programme with common features. It specifies: the scope of what is funded; the reimbursement rate; specific evaluation criteria to qualify for funding; and the use of simplified forms of costs like lump sums.
Funding scheme (or “Type of Action”) inside a programme with common features. It specifies: the scope of what is funded; the reimbursement rate; specific evaluation criteria to qualify for funding; and the use of simplified forms of costs like lump sums.
HORIZON-TMA-MSCA-PF-EF - HORIZON TMA MSCA Postdoctoral Fellowships - European Fellowships
See all projects funded under this funding scheme
Call for proposal
Procedure for inviting applicants to submit project proposals, with the aim of receiving EU funding.
Procedure for inviting applicants to submit project proposals, with the aim of receiving EU funding.
(opens in new window) HORIZON-MSCA-2025-PF
See all projects funded under this callCoordinator
Net EU financial contribution. The sum of money that the participant receives, deducted by the EU contribution to its linked third party. It considers the distribution of the EU financial contribution between direct beneficiaries of the project and other types of participants, like third-party participants.
50009 Zaragoza
Spain
The total costs incurred by this organisation to participate in the project, including direct and indirect costs. This amount is a subset of the overall project budget.