OpenCV 5 release - New DNN engine with enhanced ONNX and LLM/VLM support, Intel, Arm, and RISC-V hardware optimizations - CNX Software

OpenCV 5 open-source computer vision library has recently been released with a brand-new DNN (Deep Neural Network) engine that provides better ONNX coverage and enables LLM/VLM support.The fifth version of the popular CV library also adds support for Intel, Arm, Qualcomm, and RISC-V hardware acceleration, improved 3D vision, and various new core features such as new data types, real N-dimensional and scalar support, and performance improvements.OpenCV 4.x supports about 22% of ONNX operators, and the new DNN engine in OpenCV 5 brings coverage to over 80%. That means models with dynamic shapes that used to fail on OpenCV 4.x, should now work, as the 5.x engine was rebuilt around a typed operation graph with proper shape inference, constant folding, and operator fusion.ONNX coverage: OpenCV 4.x vs OpenCV 5

The table below shows the main difference between OpenCV 4.x and OpenCV 5

AspectClassic engine (4.x)New engine (5.x)

Model representationOne struct per layer, walked in orderA typed graph the engine can analyze

ShapesStatic onlySymbolic, dynamic