Vrt Pipeline Compose

Use when building or composing a real-time CV pipeline from vrt model crates — wiring RfDetrSeg / DepthAnything / XFeat together, running N models on one frame, feeding the GPU results to the CPU tracker (vrt-track) + live view (vrt-viz, H.264/WebCodecs), going fast, or handling multiple cameras. Covers the async / caller-owned / one-stream idiom, not kernel internals.

kornia Updated
RF-DETR-Seg + Depth Anything V2 + a 3D tracker on one CUDA stream

File contents

kornia/vision-rt commit 33979e146d

Frequently asked questions

npx get-skill add kornia/vrt-pipeline-compose