4 Computer Vision Jobs in Südtirol
Position Overview
- Develop and optimize geometric reconstruction modules: multi-camera calibration, feature extraction and matching, structure-from-motion.
- Implement and tune optimization techniques (bundle adjustment, surface fitting, mesh refinement) for high-precision geometry.
- Integrate learned components—feature descriptors, depth priors, outlier rejection—into classical pipelines.
- Develop capture and calibration strategies that support downstream appearance and material reconstruction.
- Build robust point cloud and mesh processing workflows for cleaning, filtering, and topology repair.
- Write performant, maintainable code that scales across our production infrastructure.
|
- Build and optimize neural inverse rendering models for geometry and material estimation.
- Develop relighting and appearance decomposition pipelines using differentiable rendering techniques.
- Explore generative reconstruction approaches: diffusion-based 3D, feed-forward reconstruction networks, neural scene representations.
- Tackle challenging scenarios: specular and transparent surfaces, thin structures, complex BRDFs.
- Write clean, production-ready code and iterate on model quality and inference speed.
|
Vollzeit
Brixen, Venedig
01.01.2026
Brixen, Venedig
Ihre Aufgaben
- Zusammenarbeit bei der Konzeption und Entwicklung von Bildverarbeitungs- und Computer-Vision-Algorithmen
- Integration von Lösungen der künstlichen Intelligenz in industrielle Messsysteme und -prozesse
- Mitarbeit bei der Erstellung, Prüfung, Inbetriebnahme und Dokumentation von Prototypen und Produkten
- Design, Anpassung und Validierung unserer Software an kundenspezifische Anforderungen
- Verantwortung für die Entwicklung, Wartung und Anpassung eines oder mehrerer unserer Softwareprodukte und Bibliotheken
|
- Design and implement BRDF models and material representations, including neural and diffusion-based approaches for material acquisition and synthesis.
- Develop differentiable rendering pipelines for inverse problems: material decomposition, relighting, and appearance transfer.
- Build diffusion-based rendering pipelines that transform PBR assets into photorealistic imagery.
- Develop intrinsic image decomposition models for separating albedo, shading, and material properties from captured images.
|
