Exigences5+ ans d'exp. · Bachelor · Permis UE/AELE
Votre correspondance
01
Compétences
02
Mobile DSPsEgo-centric datasetsComputer VisionAIReal-time systemsDeep learning frameworksRobotikspatial thinkingImage FusionScene UnderstandingSchema preparation2D to 3D translation
Design, implement, and deploy lightweight scene representations to capture world-facing context signals and enable contextual triggers and panel placement for XR glasses.
Create suitable ego-centric datasets, as well as the fusion and evaluation of different foundation models for building robust object- and scene-centric representations in real-time.
Interface these representations with Gemini/Gemma variants.
01Design, implement, and deploy lightweight scene representations to capture world-facing context signals and enable contextual triggers and panel placement for XR glasses.
02Create suitable ego-centric datasets, as well as the fusion and evaluation of different foundation models for building robust object- and scene-centric representations in real-time.
03Interface these representations with Gemini/Gemma variants.
Exigences
↳Bachelor's degree in Computer Vision, Robotics, 3D sensing, a related field, or equivalent practical experience.
↳5 years of experience in Computer Vision, Robotics, or related fields.
↳Experience contributing to research in the field of 3D surface reconstruction and semantic scene understanding.
