cd /news/computer-vision/opencv-5-0-released-with-rewritten-d… · home topics computer-vision article
[ARTICLE · art-23360] src=phoronix.com pub= topic=computer-vision verified=true sentiment=↑ positive

OpenCV 5.0 Released With Rewritten DNN Engine, Built-In LLM & VLM Support

OpenCV 5.0 was released today as a major update to the open-source computer vision library, featuring a rewritten deep neural network engine and built-in support for large language and vision language models. The new version also includes ONNX coverage exceeding 80%, a hardware abstraction layer, and an improved 3D vision toolkit, with optimized paths for Intel, Arm, Qualcomm, and RISC-V processors. Developers plan to add native GPU support to the DNN engine in future updates.

read1 min publishedJun 6, 2026

OpenCV 5.0 released today as a major update to this widely-used, open-source computer vision (CV) library.

The OpenCV library is widely-used for ral-time computer vision needs and machine learning applications. With OpenCV 5.0, it's a huge release and a major step forward in advancing its already leading capabilities.

OpenCV 5.0 features a rewritten deep neural network (DNN) engine, ONNX coverage surpassing 80%, built-in large language model (LLM) and vision language model (VLM) support, and a new hardware abstraction layer as well as a much better 3D vision toolkit.

OpenCV 5.0 currently has tuned paths for Intel IPP with SSE/AVX-optimized kernels, Arm KleidiCV, Qualcomm FastCV, and RISC-V Vector RVV. Coming up next the OpenCV developers plan to work on native GPU support within their new DNN engine.

OpenCV 5.0 is performing very well against the Microsoft ONNX Runtime:

More details on the huge release of OpenCV 5.0 via today's announcement on

The OpenCV library is widely-used for ral-time computer vision needs and machine learning applications. With OpenCV 5.0, it's a huge release and a major step forward in advancing its already leading capabilities.

OpenCV 5.0 features a rewritten deep neural network (DNN) engine, ONNX coverage surpassing 80%, built-in large language model (LLM) and vision language model (VLM) support, and a new hardware abstraction layer as well as a much better 3D vision toolkit.

OpenCV 5.0 currently has tuned paths for Intel IPP with SSE/AVX-optimized kernels, Arm KleidiCV, Qualcomm FastCV, and RISC-V Vector RVV. Coming up next the OpenCV developers plan to work on native GPU support within their new DNN engine.

OpenCV 5.0 is performing very well against the Microsoft ONNX Runtime:

More details on the huge release of OpenCV 5.0 via today's announcement on

── more in #computer-vision 4 stories · sorted by recency
sponsored brought to you by zahid.host 4,200+ EU-deployed projects
reading about agents? ship yours in a single git push.

Run your AI side-project on zahid.host

EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.

$git push zahid main
Live at https://your-agent.zahid.host
Get free account → Pricing
from €0/mo · no card required
LIVE [news/opencv-5-0-released-…] indexed:0 read:1min 2026-06-06 ·