CV

Leandro Di Bella

leandro.dibella@gmail.com
https://leandro-svg.github.io
Brussels, Belgium, BE
Website Google Scholar ORCID GitHub LinkedIn Mappx

Summary

PhD candidate at ETRO (VUB) and imec, specialized in robotics, physical AI, and computer vision for autonomous systems. Technical lead on drone localization and navigation in a European Defence Fund (EDF) research project (ORIGAMI); also working on multi-agent motion forecasting with flow-based generative AI.

Education

  • Industrial and Technological Management
    Solvay Brussels School
  • Computer Vision for Spatial and Physical Intelligence
    2026-07-01
    ICVSS — International Computer Vision Summer School (Sicily, Italy)
  • Engineering Sciences (AI, Computer Vision & Robotics)
    Vrije Universiteit Brussel (VUB)
  • Electrical Engineering (Information Technology Systems option)
    2023-01-01
    Bruface Faculty of Engineering (ULB/VUB)
  • Engineering
    2020-01-01
    Bruface Faculty of Engineering (ULB/VUB)

Work Experience

  • Technical Lead, Robotics & Perception Researcher
    2026-01-01 -
    IMEC & VUB — ORIGAMI (European Defence Fund project)
    Technical lead for drone autonomy in an EDF research project.
    • Architected and integrated the full drone platform (hardware, sensing, and autonomy software)
    • Sensor fusion and localization in 3D environments; world-model-based methods for autonomous navigation
  • Computer Vision Researcher
    2023-01-01 - 2026-01-01
    MACQ Mobility (research project)
    Perception for autonomous vehicles.
    • Detection, 3D multi-object tracking, scene understanding, and motion forecasting using generative AI
    • Achieved #1 on the KITTI MOT and Waymo motion forecasting benchmarks
  • Founder
    2025-08-01 -
    Mappx
    Launched Mappx mobile app and built the full-stack product.
    • Developed full-stack Flutter frontend and FastAPI backend integrating location-based social sharing with maps and photos
    • Implemented cost-effective backend infrastructure using Azure and Firebase to support scalable user engagement and App Store deployment
  • Intern
    2022-08-01 - 2022-10-01
    MACQ Mobility
    Developed and integrated instance segmentation on a Jetson TX2 edge device.
    • Python / C++

Skills

Programming

  • Python
  • C++
  • CUDA
  • PyTorch
  • TensorRT
  • ONNX
  • FastAPI
  • Flutter

Robotics

  • ROS 2
  • SLAM
  • Localization
  • Motion planning
  • Navigation
  • Sensor fusion

ML / Perception

  • Detection
  • Instance segmentation
  • Monocular 3D
  • 2D/3D multi-object tracking
  • Kalman filtering
  • Temporal consistency

Vision-language & GenAI

  • Grounding / referring tracking
  • Multimodal reasoning
  • Generative motion forecasting

Tools/Platforms

  • Jetson
  • Docker
  • Azure Cloud Services
  • Firebase
  • GitHub CI/CD

Publications

  • FlowS: One-Step Motion Prediction via Local Transport Conditioning
    2026
    IEEE Robotics and Automation Letters (RA-L), accepted
    One-step multi-agent motion prediction; ranked #1 on the Waymo motion forecasting benchmark.
    View Publication
  • Spectral-Aware Multi-Object Tracking in Harsh Aerial Perception Domains
    2026
    IEEE ICRA 2026 Workshop S2S
    Multi-object tracking with multispectral cues for robust aerial perception.
    View Publication
  • HybridTrack: A Hybrid Approach for Robust Multi-Object Tracking
    2025
    IEEE Robotics and Automation Letters (RA-L) / ICRA
    Data-driven Kalman filtering for 3D MOT; ranked #1 on the KITTI MOT benchmark.
    View Publication
  • ReferGPT: Towards Zero-Shot Referring Multi-Object Tracking
    2025
    IEEE/CVF CVPR Workshops
    Zero-shot referring MOT with multi-modal large language models.
    View Publication
  • ChronoFusion: Spatio-Temporal Super-Resolution based on Graph VAEs and Gated Fusion
    2025
    EUVIP
    Spatio-temporal super-resolution with graph VAEs and gated fusion.
    View Publication
  • LAM3D: Leveraging Attention for Monocular 3D Object Detection
    2024
    IEEE MMSP
    Attention mechanisms for monocular 3D object detection.
    View Publication
  • Monokalman: Monocular Vehicle Pose Estimation with Kalman Filter-Based Temporal Consistency
    2024
    IEEE MDM
    Kalman-based temporal consistency for monocular pose estimation.
    View Publication
  • DeepKalPose: An Enhanced Deep-Learning Kalman Filter for Temporally Consistent Monocular Vehicle Pose Estimation
    2024
    Electronics Letters
    Deep-learning Kalman filter for temporally consistent pose estimation.
    View Publication

Presentations

  • Talk 1 on Relevant Topic in Your Field
    2012
    UC San Francisco, Department of Testing
    San Francisco, CA, USA
  • Tutorial 1 on Relevant Topic in Your Field
    2013
    UC-Berkeley Institute for Testing Science
    Berkeley, CA, USA
  • Talk 2 on Relevant Topic in Your Field
    2014
    London School of Testing
    London, UK
  • Conference Proceeding talk 3 on Relevant Topic in Your Field
    2014
    Testing Institute of America 2014 Annual Conference
    Los Angeles, CA, USA

Teaching

  • Teaching experience 1
    2014
    University 1, Department
    Role: Undergraduate course
  • Teaching experience 2
    2015
    University 1, Department
    Role: Workshop

Portfolio

  • Portfolio item number 1
    Portfolio
    Short description of portfolio item number 1
    View Project

Languages

  • French
    Native
  • English
    C1
  • Dutch
    B1

Interests

  • Perception for autonomous systems
  • World models for perception and navigation
  • Localization in 3D environments
  • Vision-language-action (VLA) models for robotics
Download CV as PDF View Markdown CV