Post

Excited to share that two papers from the lab were accepted to #IEEE #EMBC2026 (@embs.org)! 🎉 1. Better symbol design for reading with (future) prosthetic vision 2. Cloud-adaptive preprocessing for visual neuroprostheses under real-world network constraints #BionicVision #NeuroTech

Bionic Vision Lab

@bionicvisionlab.org

Jasmine Lesner asked: in a future implant that supports reading, can we redesign the symbols themselves to make them easier to tell apart through a highly constrained visual channel? SymbolSight optimizes the symbol set, not the HW. bionicvisionlab.org/publications... #EMBC2026 #BionicVision

bionicvisionlab.orgSymbolSight: Minimizing inter-symbol interference for reading with prosthetic vision | Bionic Vision LabWe present SymbolSight, a computational framework that selects symbol-to-letter mappings to minimize confusion among frequently adjacent letters. Using simulated prosthetic vision (SPV) and a neural p...

18/4/26, 4:23 pm0 reposts0 likes

Bionic Vision Lab

@bionicvisionlab.org

18 Apr

Jiayi Liu and Yilin Wang asked: if future prosthetic vision systems use #cloud-based #AI, can they remain usable when latency, jitter, and bandwidth fluctuate? This paper studies real-time adaptation under network constraints. bionicvisionlab.org/publications... #EMBC2026 #BionicVision

bionicvisionlab.orgNetwork-adaptive cloud preprocessing for visual neuroprostheses | Bionic Vision LabWe present a network-adaptive pipeline for cloud-assisted visual preprocessing of artificial vision, where real-time round-trip-time (RTT) feedback is used to dynamically modulate image resolution, co...