
Master Thesis: Monocular XR Object Localization with World Models
Ericsson ABSammanfattning
This opportunity involves a thesis project focused on enhancing metric localization of distant moving objects in extended reality (XR) applications using pretrained world models. The role is based in Stockholm, Sweden, and includes building a video capture pipeline, training a lightweight model, and evaluating the system's performance against existing methods. This position offers a chance to contribute to innovative XR and AI solutions at Ericsson, a company committed to diversity and inclusionDet här erbjuder vi
Opportunity to work on innovative XR and AI solutions.Collaborative environment with diverse innovators.Commitment to diversity and inclusion within the organization.
Ansök senast: Öppet tillsvidare
Publicerad: 2026-10-29
Beskrivning
Join our Team
About this opportunity:
Extended reality (XR) applications need reliable estimates of object distance and motion. However, future lightweight XR and AI glasses may not include dedicated depth sensors because of cost, power, and form-factor constraints.
This thesis will investigate whether a pretrained world model, such as NVIDIA Cosmos, can use semantic and scale-related priors to improve metric localization of distant moving objects from monocular XR video. The approach will be evaluated against built-in depth sensing and conventional monocular depth estimation.
What you will do:
The skills you bring:
We are looking for a candidate who:
Why join Ericsson?At Ericsson, you'll have an outstanding opportunity. The chance to use your skills and imagination to push the boundaries of what's possible. To build solutions never seen before to some of the world's toughest problems. You'll be challenged, but you won't be alone. You'll be joining a team of diverse innovators, all driven to go beyond the status quo to craft what comes next.
What happens once you apply? Click Here to find all you need to know about what our typical hiring process looks like.Encouraging a diverse and inclusive organization is core to our values at Ericsson, that's why we champion it in everything we do. We truly believe that by collaborating with people with different experiences we drive innovation, which is essential for our future growth. We encourage people from all backgrounds to apply and realize their full potential as part of our Ericsson team. Ericsson is proud to be an Equal Opportunity Employer. learn more.
Primary country and city: Sweden (SE) || Stockholm
Req ID: 793531
About this opportunity:
Extended reality (XR) applications need reliable estimates of object distance and motion. However, future lightweight XR and AI glasses may not include dedicated depth sensors because of cost, power, and form-factor constraints.
This thesis will investigate whether a pretrained world model, such as NVIDIA Cosmos, can use semantic and scale-related priors to improve metric localization of distant moving objects from monocular XR video. The approach will be evaluated against built-in depth sensing and conventional monocular depth estimation.
What you will do:
- Build a headset (e.g. Quest 3) RGB-video capture pipeline with server-side inference.
- Keep the world model backbone frozen and train a lightweight probe to estimate object distance and motion.
- Evaluate the system in controlled scenes with walking people and moving objects, using measured ground truth and depth-estimation baselines.
- Assess accuracy, computational requirements, latency, and uplink requirements.
- Build a working prototype.
- Create a documented dataset and measurement setup.
- Produce quantitative accuracy and latency results.
- Write a thesis report with recommendations for camera-only XR perception and network-assisted spatial intelligence.
The skills you bring:
We are looking for a candidate who:
- Is analytical, curious, and open-minded.
- Is fluent in written and spoken English.
- Is studying XR and spatial understanding as a key focus of their Master's degree at a university.
- Has good knowledge of Unity and MR/VR programming.
- Has previous experience writing applications for the Meta Quest family of headsets; this is an advantage.
- Shares Ericsson's core values of Professionalism, Perseverance, Respect, and Integrity.
Why join Ericsson?At Ericsson, you'll have an outstanding opportunity. The chance to use your skills and imagination to push the boundaries of what's possible. To build solutions never seen before to some of the world's toughest problems. You'll be challenged, but you won't be alone. You'll be joining a team of diverse innovators, all driven to go beyond the status quo to craft what comes next.
What happens once you apply? Click Here to find all you need to know about what our typical hiring process looks like.Encouraging a diverse and inclusive organization is core to our values at Ericsson, that's why we champion it in everything we do. We truly believe that by collaborating with people with different experiences we drive innovation, which is essential for our future growth. We encourage people from all backgrounds to apply and realize their full potential as part of our Ericsson team. Ericsson is proud to be an Equal Opportunity Employer. learn more.
Primary country and city: Sweden (SE) || Stockholm
Req ID: 793531
Ansök till tjänsten
Master Thesis: Monocular XR Object Localization with World Models
OM FÖRETAGET

Ericsson AB










