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

<br><strong>Abstract</strong><p><span style="font-family:Arial, Helvetica, sans-serif;font-size:14px;color:rgb(0,0,0);">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.</span><br><span style="font-size:14px;color:rgb(0,0,0);"><br></span><span style="font-family:Arial, Helvetica, sans-serif;font-size:14px;color:rgb(0,0,0);">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.</span><br><span style="font-size:14px;color:rgb(0,0,0);"><br></span><span style="font-family:Arial, Helvetica, sans-serif;font-size:14px;color:rgb(0,0,0);">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.</span></p><br><strong>These tasks interest you</strong><p><ul><li><span style="font-family:Arial, Helvetica, sans-serif;font-size:14px;color:rgb(0,0,0);"><strong>Develop and evaluate feed-forward 3D reconstruction models</strong> for dynamic scenes using monocular or multi-view image sequences.</span></li><li><span style="font-family:Arial, Helvetica, sans-serif;font-size:14px;color:rgb(0,0,0);"><strong>Investigate reconstruction robustness</strong> under partial and long-term occlusions, moving objects, and incomplete observations.</span></li><li><span style="font-family:Arial, Helvetica, sans-serif;font-size:14px;color:rgb(0,0,0);"><strong>Develop methods to improve geometric consistency</strong> under illumination changes, low-light conditions, shadows, and reflections.</span></li><li><span style="font-family:Arial, Helvetica, sans-serif;font-size:14px;color:rgb(0,0,0);"><strong>Evaluate and improve model performance</strong> under adverse weather conditions such as rain, fog, snow, and reduced visibility.</span></li><li><span style="font-family:Arial, Helvetica, sans-serif;font-size:14px;color:rgb(0,0,0);"><strong>Compare the developed methods</strong> with relevant baselines and document technical and experimental results.</span></li></ul></p><br><strong>That makes you stand out</strong><p><ul><li><span style="font-family:Arial, Helvetica, sans-serif;color:rgb(0,0,0);font-size:14px;">You are <strong>currently pursuing a degree in computer science, artificial intelligence, robotics, electrical engineering, data science,</strong> or a related field.</span></li><li><span style="font-family:Arial, Helvetica, sans-serif;color:rgb(0,0,0);font-size:14px;">You have <strong>excellent programming skills in Python</strong> as well as hands-on experience with <strong>PyTorch</strong>.</span></li><li><span style="font-family:Arial, Helvetica, sans-serif;color:rgb(0,0,0);font-size:14px;">You have a <strong>good understanding of computer vision, deep learning, 3D geometry</strong>, or <strong>multi-view vision</strong>.</span></li><li style="font-family:Arial, Helvetica, sans-serif;font-size:14px;color:rgb(0,0,0);">Experience with depth estimation, optical flow, point clouds, camera pose estimation, NeRF, 3D Gaussian Splatting, or 3D reconstruction is highly beneficial.</li><li><span style="font-family:Arial, Helvetica, sans-serif;color:rgb(0,0,0);font-size:14px;">Your language skills enable you to perform your role in <strong>English (at least C1 level)</strong>. Knowledge of German is desirable but not required.</span></li></ul></p><br><strong>Salary information</strong><p><span style="font-family:Arial, Helvetica, sans-serif;color:rgb(0,0,0);font-size:14px;">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.</span></p><br><strong>Your contact person</strong><p><strong><span style="color:rgb(0,0,0);font-family:Arial, Helvetica, sans-serif;font-size:14px;">Daniela</span></strong><span style="color:rgb(0,0,0);font-family:Arial, Helvetica, sans-serif;font-size:14px;"><br>+49 821 885882-0</span><br><span style="color:rgb(0,0,0);font-family:Arial, Helvetica, -----<p>Find more <a href="https://www.arbeitnow.com/english-speaking-jobs">English Speaking Jobs in Germany</a> on Arbeitnow</a>