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

Xitaso · Augsburgjunior

En corto

▸Desarrollar modelos de reconstrucción 3D feed-forward para escenas dinámicas con imágenes monoculares o multivistas.
▸Enfocarse en mejorar la robustez ante occlusiones, cambios de iluminación, mal tiempo y objetos en movimiento.
▸Destaca por usar modelos grandes preentrenados como núcleo geométrico para tareas 3D y 4D de comprensión de escenas.

At least C1 level

En ~1 minuto te damos: quién te entrevista, las preguntas probables con respuestas desde tu CV, y tu CV adaptado a esta vacante. Gratis, sin tarjeta.

🎧¿Llegás a la entrevista? Llevá el copiloto. Nuestra extensión escucha la entrevista en vivo y te muestra anclas de 3-4 palabras desde tu CV y tu preparación — mirás, conectás, hablás. Gratis. Ver la extensión →

¿Qué piden?

✓Estudiante de Ciencias de la Computación, IA, Robótica, Ingeniería Eléctrica, Ciencia de Datos o campo relacionado.
✓Excelentes habilidades en Python y experiencia práctica con PyTorch.
✓Conocimiento sólido en visión por computadora, aprendizaje profundo, geometría 3D o visión multivista.
✓Experiencia previa con estimación de profundidad, flujo óptico, nubes de puntos, estimación de pose de cámara, NeRF, 3D Gaussian Splatting o
✓Nivel C1 en inglés (requerido para desempeñar el rol).
✓Disponibilidad para trabajar 20 horas semanales (indicado como 'working student')

¿No cumplís todo? Es lo normal — tu dossier gratis te dice qué gaps tenés y cómo cubrirlos en la entrevista.

PythonPyTorchComputer VisionDeep Learning3D GeometryMulti-View VisionDepth EstimationOptical FlowPoint CloudsCamera Pose Estimation

¿A quién escribirle en Xitaso?

Tu dossier gratis identifica a las personas que te entrevistarían — con su background, qué valoran y cómo escribirles para destacar antes de aplicar.

Abstract Feed-forward 3D reconstruction models can recover scene geometry directly from images or videos without costly scene-specific optimization. By combining large-scale pre-training, multi-view reasoning, and strong geometric priors, these models provide an efficient alternative to traditional reconstruction pipelines such as Structure-from-Motion, NeRF, and optimization-based 3D Gaussian Splatting. Despite recent progress, current models remain sensitive to challenging real-world conditions. Occlusions, moving objects, illumination changes, nighttime scenes, reflections, rain, fog, and snow can result in incomplete geometry, unreliable correspondences, and temporally inconsistent predictions. Improving robustness under such conditions is essential for autonomous driving and robotic perception. As a working student, you will support the development of robust feed-forward reconstruction models for dynamic scenes. You will investigate methods for handling occlusion, changing illumination, and adverse weather, and explore how large reconstruction models can serve as general-purpose geometric backbones for downstream 3D scene understanding, particularly semantic occupancy prediction and 4D occupancy forecasting. These tasks interest you 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 such as rain, fog, snow, and reduced visibility. Compare the developed methods with relevant baselines and document technical and experimental results. That makes you stand out You are currently pursuing a degree in computer science, artificial intelligence, robotics, electrical engineering, data science, or a related field. You have excellent programming skills in Python as well as hands-on experience with PyTorch . You have a good 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. Your language skills enable you to perform your role in English (at least C1 level) . Knowledge of German is desirable but not required. Salary information Within our standardized and transparent salary framework, the pay for this position ranges from €15.50 to €19.50 per hour and is based on various factors, such as qualifications and experience.

No apliques sin prepararte

Investigamos quién te entrevista, adaptamos tu CV y te ensayamos en vivo — gratis la primera.