Event cameras and edge inference: why the frame-based mindset is still holding us back

So, the thing is, most edge inference pipelines for computer vision are built around a mental model that goes: capture frame → preprocess → run model → get result → repeat. Everything is designed around this loop. The latency budget, the model architecture, the preprocessing pipeline, the hardware selection — all of it assumes that "input" means "a dense grid of pixel values captured at a regular interval." This works. For many applications it works well. But there's a class of problems where t