uzh-rpg/event-based_vision_resources

Event-based Vision Resources. Community effort to collect knowledge on event-based vision technology (papers, workshops, datasets, code, videos, etc)

What it solves

This project provides a comprehensive, curated directory of resources for event-based vision, a field that uses specialized cameras to capture motion and changes in light intensity with extremely low latency. It helps researchers and developers navigate the complex landscape of hardware, algorithms, and academic literature in this specialized area of computer vision.

How it works

The repository acts as a centralized knowledge hub. It organizes information into structured categories, including:

  • Hardware & Manufacturers: Details on various Dynamic Vision Sensors (DVS) and Hybrid Vision Sensors (HVS), including technical specifications and commercial availability.
  • Algorithms & Applications: A vast list of research papers and implementations covering tasks like SLAM, optical flow, object recognition, and signal processing.
  • Software & Tools: Links to drivers, simulators, and synthetic data generators for testing event-based systems.
  • Academic Resources: A collection of survey papers, theses, and information on upcoming workshops and conferences.

Who it’s for

This resource is designed for researchers, students, and engineers working in neuromorphic engineering, robotics, autonomous systems, and computer vision who need a reliable starting point to explore or contribute to the event-based vision community.

Highlights

  • Extensive list of event-based vision hardware, from research prototypes to commercial sensors.
  • Categorized bibliography of academic papers covering everything from basic signal processing to complex 3D reconstruction.
  • Links to active software ecosystems, simulators, and synthetic data generators.
  • Directory of key institutions and companies currently advancing the field.
  • Regularly updated list of upcoming academic workshops and paper calls.

Related

  • Project
    opengeos/geoai

    A Python package that integrates AI frameworks with geospatial data analysis, providing tools for satellite imagery processing, model training, and inference.

  • Project
    xinghaochen/awesome-hand-pose-estimation

    awesome-hand-pose-estimation is a curated list of research papers, datasets, and resources on hand pose estimation. It organizes entries by source (arXiv, journals, conferences), year (2014–2025), and topic (datasets, workshops, challenges, theses). Each entry links to the paper's PDF and sometimes to code or project pages. It is a reference list, not a software tool, and invites community contributions.

  • Project
    roflcoopter/viseron

    A self-hosted, local-only NVR and AI computer vision software for home and office monitoring with object and face recognition.

  • Project
    M-3LAB/awesome-industrial-anomaly-detection

    M-3LAB/awesome-industrial-anomaly-detection is a curated, community-maintained list of research papers, benchmarks, and code for AI-based defect detection in manufacturing. It organizes the field by method type (unsupervised, supervised, zero/few-shot, etc.), lists state-of-the-art methods with code, and tracks recent publications by conference. It also highlights several notable resources: AD-Copilot (an AI assistant that reportedly beats humans on real inspection tasks), the MMAD benchmark for evaluating multimodal language models, and the IM-IAD benchmark. The repository is a reference index, not a tutorial — it points to papers and code rather than explaining methods itself.