Wiring Android's MediaPipe Graph API to TensorFlow Lite for Custom On-Device Pipelines: Beyond the Pre-Built Tasks

Most coverage stops at MediaPipe's high-level Task API. This digs into the graph-level API: building custom CalculatorGraphs in C++ with JNI bridges, wiring TFLite delegates directly into calculator nodes, managing packet timestamps for streaming inference, and the zero-copy GPU texture path that keeps frame pipelines under 16ms on mid-range Snapdragon hardware.