ProfileComputer Vision Engineer specializing in neural 3D scene representations, Gaussian Splatting, and large-scale reconstruction systems. Experienced in building Neural based pipelines, multi-view geometry systems, and synthetic data generation for real-world applications. Focused on research-driven development of scalable 3D understanding and spatial computing systems, with growing interest in extending these approaches to dynamic and temporally consistent representations.
Skills- 3D Vision & Geometry: NeRFs, Gaussian Splatting, SFM, SMPL/ SMPL-X, Multiview Geometry, Point Clouds, Camera Calibration
- Systems & Tools: Unity3D, Blender, MeshLab, NeRF Studio, Meshroom, EasyMocap, ARKit, RoomPlan, CVAT, LabelMe
- Vision Libraries & Platforms: OpenCV, Open3D, Panda3D, Trimesh, ROS2, Docker, GCP, Segment Anything, VLMs, Vision Transformer
- Programming & ML Frameworks: Python, C++, PyTorch, TensorFlow, Three.js, TensorBoard, Weights & Biases
Experience10/2025 - 11/2025Kukan, Bendorf (Germany)
Computer Vision Engineer (Contract)
- Developed a room-scale geometry capture pipeline using ARKit and RoomPlan, converting spatial depth data into structured point clouds and refined mesh representations
- Trained and deployed 3D Gaussian Splat models from captured imagery, integrating splat-based photorealistic rendering into a Three.js web viewer for interactive spatial exploration
- Created a collision-aware navigation system using BVH-accelerated physics. Facilitated human-like room-to-room traversal instead of direct teleportation
07/2024 - 06/2025Kaptura GmbH, Bendorf (Germany)
Computer Vision Engineer
- Developed NeRF and Gaussian Splatting pipelines for a large-scale multi-camera 3D scanning system, (~250 cameras) improving reconstruction stability and fidelity
- Built a 2D?3D camera - LED calibration & tracking pipeline with custom markers and homography-based correction; reduced calibration time (~2.5 hours to ~30 minutes)
- Applied SfM and multi-view geometry to refine camera poses and mitigate drift, scale & alignment errors; reduced RMSE (~4.8 to ~2.1) and stabilized reconstructions
- Investigated reconstruction of reflective and transparent objects using hybrid rasterization and ray-tracing approaches
- Containerized applications with Podman and integrated ROS and Streamlit to control scanning system components efficiently
10/2021 - 06/2024Technical University of Chemnitz (Germany)
Research Assistant - Computer Vision
- Generated synthetic 3D datasets and reconstructed indoor environments (~500 scenes) using Unity3D and NeRF pipelines
- Developed simulation datasets for autonomous driving perception experiments (~50?70 outdoor scenes under varied conditions) using Unity3D
- Built perception pipelines for 3D object recognition, segmentation, and tracking using point clouds, meshes and monocular 3D detection methods
- Supported dataset preparation and annotation workflows for human pose and object understanding tasks
01/2023 - 02/2024Technical University of Chemnitz (Germany)
Research Experience - Computer Vision
- Built a NeRF and Gaussian Splatting based large-scale dataset (~600K images) for fisheye-view human reconstruction and pose estimation
- Trained neural rendering and pose estimation models using multi-GPU workflows; implemented fine-tuning strategies to extend reconstructions across multiple poses without full retraining
- Integrated SAM, GroundingDINO, and Vision Transformers for automated human segmentation and scene understanding
- Generated SMPL-X / SMPL-H meshes and evaluated downstream 2D/3D pose estimation pipelines for reconstruction accuracy and robustness