Prophesee launches the world’s smallest and most power-efficient event-based vision sensor, bringing more intelligence, privacy and safety than ever to consumer Edge-AI device

Prophesee SA, inventor of the world’s most advanced neuromorphic vision systems, announced the availability of the GenX320 Event-based Metavision sensor, the industry’s first event-based vision sensor developed specifically for integration into ultra-low-power Edge AI vision devices. The fifth generation Metavision sensor, available in a tiny 3x4mm die size, expands the reach of the company’s pioneering technology platform into a vast range of fast-growing intelligent Edge market segments, including AR/VR headsets, security and monitoring/detection systems, touchless displays, eye tracking features, always-on smart IoT devices and many more.

The GenX320 event-based vision sensor builds on Prophesee’s track record of proven success and expertise in delivering the speed, low latency, dynamic range and power efficiency and privacy benefits of event-based vision to a diverse array of applications.

The 320×320 6.3μm pixel BSI stacked event-based vision sensor offers a tiny 1/5” optical format. It has been developed with a specific focus on the unique requirements of efficient integration of innovative event sensing in energy-, compute and size-constrained embedded at-the-edge vision systems. The GenX320 enables robust, high-speed vision at ultra-low power and in challenging operating and lighting conditions.

GenX320 benefits include:

  • Low latency µsec resolution timestamping of events with flexible data formatting.
  • On-chip intelligent power management modes reduce power consumption to as low as 36uW and enable smart wake-on-events. Deep sleep and standby modes are also featured.
  • Easy integrability/interfacing with standard SoCs with multiple integrated event data preprocessing, filtering, and formatting functions to minimize external processing overhead.
  • MIPI or CPI data output interfaces offer low-latency connectivity to embedded processing platforms, including low-power microcontrollers and modern neuromorphic processor architectures.
  • AI-ready: on-chip histogram output compatible with multiple AI accelerators;
  • Sensor-level privacy-enabled thanks to event sensor’s inherent sparse frameless event data with inherent static scene removal.
  • Native compatibility with Prophesee Metavision Intelligence, the most comprehensive, free, event-based vision software suite, used by a fast-growing community of 10,000+ users.

“The low-power Edge-AI market offers a diverse range of applications where the power efficiency and performance characteristics of event sensors are ideally suited. We have built on our foundation of commercial success in other application areas and developed this new eventbased Metavision sensor to address the needs of Edge system developers with a sensor that is easy to integrate, configure and optimize for multiple compelling use cases in motion and object detection, presence awareness, gesture recognition, eye tracking, and other high growth areas,” said Luca Verre, CEO and co-founder of Prophesee.

Specific use case potential

  • High-speed eye-tracking for foveated rendering for seamless interaction in AR/VR/XR headsets
  • Low latency touch-free human-machine interface in consumer devices (TVs, laptops, game consoles, smart home appliances and devices, smart displays and more)
  • Smart presence detection and people counting in IoT cameras and other devices
  • Ultra-low power always-on area monitoring systems
  • Fall detection cameras in homes and health facilities


The GenX320 is available for purchase from Prophesee and its sales partners. It is supported by a complete range of development tools for easy exploration and optimization, including a comprehensive Evaluation Kit housing a chip on board (COB) GenX320 module, or a compact optical flex module. In addition, Prophesee is offering a range of adapter kits that enable seamless connectivity to a large range of embedded platforms, such as an STM32 MCU, enabling faster time-to-market.