Master Thesis – Core Tech Graphics: Three Different Ideas

Axis Communications offers three master's thesis topics exploring AI and computer vision for camera-based scene understanding. The options focus on updating digital twins, aligning visual and thermal images, or improving depth estimation and segmentation in body-worn video. Each topic investigates methods that could support more reliable image interpretation or 3D reconstruction.

The assignment

• Option 1 — Digital twins: Develop methods to detect and segment scene changes, compare monocular depth models, and evaluate how accurately new objects can be positioned in a digital twin without repeated scans.
• Option 2 — Visual–thermal alignment: Review relevant research, implement or adapt shared-feature detection methods, and compare their ability to align paired visual and thermal images.
• For Option 2, investigate conditions affecting alignment, identify data and calibration needs, and deliver a demonstration with findings and recommendations.
• Option 3 — Body-worn video: Build a depth-estimation and segmentation baseline using pre-trained V-JEPA features and task-specific prediction modules.
• For Option 3, investigate training objectives, combinations of features from different model layers, and information across frames to improve prediction consistency.
• Evaluate Option 3 results and their impact on indoor reconstruction through an existing 3D pipeline.

Who we are looking for

• Master's students in computer science, applied mathematics, engineering physics, electronics engineering, or a related discipline.
• Applicants must be enrolled at a Swedish university or university college, either directly or through an exchange programme.
• Students applying as a pair.

What we offer

• A choice of three research topics addressing practical challenges in AI and computer vision.
• The body-worn camera project combines hands-on programming with research in video world models and 3D vision, involving collaboration across Axis teams.
• An open, friendly and collaborative company culture with an emphasis on developing skills and ways of working.

Practical details

Location: Lund. Scope: 30 credits for two master's students. Apply through the thesis advert by 27 November 2026; applications may be written in Swedish or English. Submit separate applications, name your thesis partner, and indicate which topic or topics interest you. Include your CV and university grade summary. Questions: Sara Garmark, hiring manager, +46 46 287 97 77.