Publisher
source

Fondazione Bruno Kessler

PhD Candidate - Structured Semantic Enhancement of 3D Scene Representations Fondazione Bruno Kessler in Italy

Degree Level

PhD

Field of study

Computer Science

Funding

Full funding available

Deadline

Aug 27, 2026

Country flag

Country

Italy

University

Fondazione Bruno Kessler

Social connections

How do I apply for this?

Sign in for free to reveal details, requirements, and source links.

More information can be found here

Keywords

Computer Science
Electrical Engineering
Artificial Intelligence
Photogrammetry
Computer Vision
Semantic Segmentation
Robotics
Point Cloud

Suggested positions

About this position

Fondazione Bruno Kessler is offering a PhD position on Structured Semantic Enhancement of 3D Scene Representations. The project focuses on converting raw 3D observations into structured, reusable scene representations that combine geometry, object-level organization, and semantic information. The research is positioned at the intersection of artificial intelligence, 3D computer vision, and neural scene representation learning.

The PhD will explore methods inspired by neural reconstruction pipelines such as Gaussian Splatting, together with 3D sensing technologies including LiDAR and photogrammetry. A central goal is to make unstructured 3D data more useful for downstream applications such as mapping, simulation, and analysis by transforming it into coherent digital assets.

Research objectives include developing new neural scene representation methods and comparing them with conventional geometric approaches; decomposing raw 3D scenes into consistent object-level components with semantic categories and attributes; refining incomplete or ambiguous regions into coherent structures; studying semantic propagation across spatially connected regions; and improving robustness across heterogeneous environments such as indoor, outdoor, and natural settings.

Ideal applicants will have a strong background in artificial intelligence and 3D computer vision, solid programming skills, and a genuine interest in 3D data processing, including point clouds and neural scene representations. Familiarity with foundation models, such as vision-language models, is also highlighted as an advantage, alongside the ability to build innovative, reliable, and reproducible solutions for challenging 3D scene understanding problems.

The position is a full-time temporary PhD opening in Povo/Trento, Italy, at Fondazione Bruno Kessler. The start date is listed as 1 November 2026, and the application deadline is 27 August 2026 at 23:59 (Europe/Rome). Applicants are expected to hold a Master Degree or equivalent. Interested candidates should apply via the official FBK PhD call page.

Funding details

Full funding including tuition fees and living expenses is available for this position. The scholarship covers all educational costs and provides a monthly stipend.

How to apply

Please submit your application including a cover letter, CV, academic transcripts, and contact information for two references. Applications should be sent via the online portal before the deadline.

Ask ApplyKite AI

Start chatting
Can you summarize this position?
What qualifications are required for this position?
How should I prepare my application?