On Hacker News
OpenCV 5 Is Here: The Biggest Leap in Years for Computer Vision
347
points
56
comments
1
notable voices
The 5-second version
- OpenCV 5 features a completely rebuilt DNN engine with ONNX operator coverage jumping from ~22% to over 80%, enabling modern models with control flow and dynamic shapes to run out of the box.
- The new graph-based engine supports LLMs, VLMs, diffusion models, and modern architectures like transformers through improved shape inference, constant folding, and operator fusion.
- Hardware acceleration is significantly improved with a cleaner HAL architecture, better Python integration with named arguments, and native FP16/BF16 support for efficient cross-platform deployment.
- The core library is faster and leaner with the legacy C API retired, proper 0D/1D tensor support, real logging, and expanded 3D vision capabilities including ChArUco and multi-camera calibration.
- Upcoming roadmap includes native GPU support in the DNN engine and a non-CPU HAL for accelerated pre/post-processing, with pip release scheduled for June 8, 2026.
Top voices
Verbatim comments from the thread's most notable / highest-karma participants.
It's certainly a choice to make your headline feature a new ONNX engine, feature a bunch of comparisons how it's better than ONNXRuntime, while casually mentioning on the side that the cool new much faster engine is CPU-only Sure, running models on the CPU is very much a thing in computer vision (the benchmarked YOLOv8n has 37M params). But this whole announcement feels more like OpenCV catching up to the modern world, not "The Biggest Leap in Years for Computer Vision" Still great, needing fe…Read on HN ↗
They can however be extremely useful for curating training data. Also things like SAM and the DINO (/grounding dino) models. Also if they are better then you can also have a flow that’s cheap model -> marginal cases go to more complex thing (and a chain of these). The yolo models are really shockingly good for their cost and how well they can work with not much training data as well.Read on HN ↗
serf10.8k karma
do you realize how many edge or unconnected nodes do OpenCV work? some SBC w/ an industrial camera that is doing pick-place or go/no-go operations on a conveyor belt against a singular object type doesn't need a huge image-gen/llm model governing it. I mean have you even considered the kind of performance an opencv function can get w/ just mask-matching? I mean even with a fancy YOLO model these answers get thrown out in 1.5-50ms ; this is just a wholly different time scaling.Read on HN ↗
kryptiskt10.4k karma
If I want to identify and measure the size of round things in my orange sorter machine, I shouldn't have to resort to an unnecessarily complicated solution just because some AI bros can't understand that not everything needs to be an AI model. Like, the AI model tools already exist, all that would be accomplished if OpenCV pivoted would be to take it away for people who want to do low-level vision programming. It wouldn't add anything useful to the world, just destroy an excellent library.Read on HN ↗