collaborators

14 papers

cs.CV2026

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…

cs.CV2026

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…

cs.CV2026

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…

cs.CV2026

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…

cs.CV2026

FTerViT: Fully Ternary Vision Transformer

Szymon Ruciński, 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,…

cs.HC2026

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…