Working Student (all genders) – Robust Feed-Forward 3D Reconstruction for Dynamic Scene

About This Opportunity

Our talent team is representing a confidential technology organization in Augsburg that is advancing the state of the art in 3D scene understanding. We are seeking a Working Student to contribute to research and development of robust feed-forward 3D reconstruction models for dynamic environments.

Feed-forward 3D reconstruction models recover scene geometry directly from images or videos without scene-specific optimization. By leveraging large-scale pre-training, multi-view reasoning, and geometric priors, these models offer efficient alternatives to traditional pipelines. However, real-world conditions—occlusions, moving objects, illumination changes, adverse weather, nighttime scenes, reflections, rain, fog, and snow—remain challenging. This role focuses on improving model robustness under such conditions, with applications in autonomous driving and robotic perception.

Responsibilities

• Develop and evaluate feed-forward 3D reconstruction models for dynamic scenes using monocular or multi-view image sequences
• Investigate reconstruction robustness under partial and long-term occlusions, moving objects, and incomplete observations
• Develop methods to improve geometric consistency under illumination changes, low-light conditions, shadows, and reflections
• Evaluate and improve model performance under adverse weather conditions including rain, fog, snow, and reduced visibility
• Compare developed methods with relevant baselines and document technical and experimental results
• Explore how large reconstruction models can serve as geometric backbones for downstream 3D scene understanding, particularly semantic occupancy prediction and 4D occupancy forecasting

What We're Looking For

• Currently pursuing a degree in computer science, artificial intelligence, robotics, electrical engineering, data science, or a related field
• Excellent programming skills in Python with hands-on experience using PyTorch
• Strong understanding of computer vision, deep learning, 3D geometry, or multi-view vision
• Experience with depth estimation, optical flow, point clouds, camera pose estimation, NeRF, 3D Gaussian Splatting, or 3D reconstruction is highly beneficial
• English language proficiency at C1 level or higher; German knowledge is desirable but not required
• Located in or able to work from Augsburg

How We Work With You

Candidates apply directly through Get A Job.ai. Our recruiting team will screen your application and arrange an initial conversation to understand your background and goals. If there is a strong mutual fit, we will submit your profile to our client for consideration. Please do not contact the client organization directly, as all communication is managed through our team to ensure a professional and coordinated process.

Pay

Pay via Get A Job.ai: €15.50–€19.50 per hour, based on qualifications and experience.

Equal Employment Opportunity: Get A Job.ai is committed to creating an inclusive recruitment process. We welcome applications from candidates of all backgrounds and provide equal opportunity throughout our screening and placement services.