The growing adoption of wearable smart glasses and AR headsets is enabling a new generation of on-device AI systems that interact naturally with users and their environments. Eye tracking lies at the heart of this evolution, providing real-time measurements of gaze direction, pupil dynamics, and visual attention, critical for truly immersive and responsive experiences. Despite significant advances in gaze estimation algorithms, hardware and embedded systems remain a key bottleneck, preventing efficient always-on deployment on resource-constrained devices.
The SPHERA Workshop at ETRA 2026 brings together researchers and practitioners working at the intersection of sensor innovation, embedded intelligence, and real-time eye-tracking technologies. Recent breakthroughs in low-power sensing, hardware acceleration, and on-device machine learning, such as miniaturized optical modules, capacitive and event-based sensors, FPGA and NPU architectures, and TinyML frameworks, offer promising paths to overcoming current limitations. By highlighting these advancements, the workshop aims to bridge the gap between algorithmic progress and deployable, energy-efficient systems capable of robust performance in real-world conditions.
The need for this workshop arises from the growing importance of tightly integrated sensing and processing pipelines that can sustain eye-tracking capabilities under strict power, latency, and form-factor constraints. As wearable devices continue to evolve, a dedicated forum is essential for consolidating interdisciplinary insights and accelerating practical adoption. Accordingly, SPHERA seeks not only to showcase emerging research but also to inspire a roadmap for the next generation of adaptive, hardware-optimized eye-tracking technologies.
June 1st 2026, Marrakech, Morocco