A real-time camera filter has about 33 milliseconds per frame at 30 FPS. When a filter that looked fine in a demo stutters on a real handset, the loss is almost always in one of five places: format conversion, frame backpressure, where inference actually executes, synchronous readback, or sustained thermal load. Here is how I find which one. TL;DR The budget is arithmetic you can do in your head: 1000 / 30 = 33.3 ms per frame, and 1000 / 60 = 16.7 ms. Converting a camera fram...