Internship - Characterizing and Optimizing Multi-View Vision Systems

inria-alumni; Montbonnot-Saint-Martin; Remote; EUR 7,800 - 12,000; Part time

Benefits offered by this job

Partial reimbursement of public travel

Teleworking up to 90 days/year

Social, cultural and sports events

Job summary

Inria Grenoble is offering an internship to characterize and optimize multi-view vision systems. You will work on a general framework to analyze how camera configurations affect 3D reconstruction quality.

The project includes building a reusable library of metrics and developing interactive 2D/3D visualization tools to analyze camera configurations and identify poorly observed regions. The role combines multi-view geometry, 3D vision, optimization, and software development, with opportunities to

Qualifications

• Master student in Computer Science, Computer Vision, Applied Mathematics, Robotics, Computer Graphics or related field.
• Strong programming skills in Python and/or C++.
• Background in computer vision, computer graphics, robotics or 3D geometry is a plus.

Responsibilities

• Develop a general framework to characterize observation capabilities of multi‑view systems.
• Implement a reusable library with metrics and interactive 2D/3D visualization tools.
• Explore camera-system optimization by adjusting camera configurations to maximize coverage and observation density.

Skills

Computer Vision

3D geometry

Robotics

Python

C++

Education

Master's degree or equivalent (M2) in CS/CV/Applied Math/Robotics/Graphics

Tools

Python

C++

Job description

Internship - Characterizing and Optimizing Multi-View Vision Systems

The Inria Grenoble research center groups together almost 600 people in 26 research teams and 8 research support departments.

Staff is present on three campuses in Grenoble, in close collaboration with other research and higher education institutions (University Grenoble Alpes, CNRS, CEA, INRAE, …), but also with key economic players in the area.

Inria Grenoble is active in the fields of high-performance computing, verification and embedded systems, modeling of the environment at multiple levels, and data science and artificial intelligence. The center is a top-level scientific institute with an extensive network of international collaborations in Europe and the rest of the world.

Context

Multi-view reconstruction aims to recover the 3D geometry of a scene from images captured by multiple cameras (e.g., [1] ). By combining observations of the same scene points from different viewpoints, multi-view methods can estimate depth and reconstruct detailed 3D surfaces. Reconstruction quality strongly depends on the camera configuration, including camera positions, orientations, focal lengths, fields of view, and image resolutions. Together, these parameters determine which parts of the scene are visible, how accurately they are observed, and how effectively their 3D geometry can be recovered. However, a general framework for quantitatively characterizing the ability of a multi-camera system to reconstruct a given 3D scene is still lacking.
Recent work on camera placement and next-best-view selection has primarily focused on coverage and observation quality. In particular, [2] investigates camera placement using learned observation fields, while [3] proposes selecting informative views by prioritizing geometry that is insufficiently covered by existing cameras. Although these approaches provide useful tools for optimizing camera configurations, they do not establish a general framework for quantitatively assessing the reconstruction capabilities of a multi-view vision system.

The goal of this internship is to develop a general framework forcharacterizing the observation capabilities of multi-view systems.

Metrics that will be investigated include:

• the number of pixels observing each voxel, leading to a3D observation density;
• the number of pixels observing each surface element, leading to asurface observation density;
• multi-view redundancy and viewing-direction distributions;
• potentially, metrics related to geometric reconstruction quality.

Part of the internship will be the development of areusable libraryimplementing these metrics together with interactive 2D/3D visualization tools for analyzing camera configurations and identifying poorly observed regions.

A more exploratory objective will be to use these metrics forcamera-system optimization. Given a target scene and an objective, the system could optimize camera positions, orientations, focal lengths, and resolutions to maximize coverage, observation density, or another task-specific criterion. This connects the project to recent work [ 3]on camera placement and active view selection.

The project combinesmulti-view geometry, 3D vision, optimization, and software development, with the possibility of pursuing research directions depending on the results.

Profile

We are looking for a highly motivated Master student M2 in Computer Science, Computer Vision, Applied Mathematics, Robotics, Computer Graphics, or a related field. Good programming skills in Python and/or C++ are required. Background in computer vision, computer graphics, robotics, or 3D geometry would be appreciated.

Avantages

• Partial reimbursement of public transport costs
• Possibility of teleworking (90 days / year) and flexible organization of working hours
• Social, cultural and sports events and activities