14 papers
PicoSAM3: Real-Time In-Sensor Region-of-Interest Segmentation
Pietro Bonazzi, Nicola Farronato, Stefan Zihlmann +2
Real-time, on-device segmentation is critical for latency-sensitive and privacy-aware applications such as smart glasses and Internet-of-Things devices. We introduce PicoSAM3, a li…
OpenGlass: Ultra-Low-Power On-Device AI Eyewear with Event-based Vision
Pietro Bonazzi, Julian Moosmann, Ahmet Celik +2
Smart eyewear enables unobtrusive, context-aware interaction through multimodal sensors and on-device intelligence, but is severely limited by power, memory, and compute constraint…
Event-Based Vision in Space: Applications, Trends, and Future Directions
Luigi Capogrosso, Pietro Bonazzi, Michele Magno
Earth Observation (EO) is undergoing a significant transformation driven by the deployment of novel sensing technologies. Traditional frame-based optical sensors often struggle wit…
Exploiting In-Sensor Computing for Energy-Efficient Earth Observation
Luigi Capogrosso, Pietro Bonazzi, Loris Hoxhaj +1
The rapid growth of the satellite industry has driven a significant increase in geospatial data acquisition, highlighting a critical bottleneck: the severe disparity between the vo…
FTerViT: Fully Ternary Vision Transformer
Szymon RuciÅski, Pietro Bonazzi, Engin Türetken +3
Ternary Vision Transformers offer substantial model compression, however state-of-the-art methods only ternarize the encoder layers, leaving patch embeddings, LayerNorm parameters,…
OpenWatch: A Multimodal Benchmark for Hand Gesture Recognition on Smartwatches
Pietro Bonazzi, Youssef Ahmed, Daniel Eckert +4
Despite widespread adoption of smartwatches worldwide, open-benchmarks for wrist-based gesture recognition remain surprisingly limited. In this work, we introduce the first open-ac…