News for hackers. Stuff that matters.
Re:OpenCV 5 Is Here: The Biggest Leap in Years for Computer ... by ftchd on Tuesday June 09, 2026 @03:38AM (#48457875)
> One practical detail is worth knowing. The new engine is CPU-only at the moment, so if you select a non-CPU backend and target (for example CUDA or OpenVINO through setPreferableBackend and setPreferableTarget), you will want the classic engine.

So there's room for even better performance!

Re:OpenCV 5 Is Here: The Biggest Leap in Years for Computer ... by wongarsu on Tuesday June 09, 2026 @04:01AM (#48458066)
It's certainly a choice to make your headline feature a new ONNX engine, feature a bunch of comparisons how it's better than ONNX Runtime, 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 fewer libraries is a good thing, but maybe a bit oversold

Re:OpenCV 5 Is Here: The Biggest Leap in Years for Computer ... by VadimPR on Tuesday June 09, 2026 @04:43AM (#48458383)
The release post is AI-written with little human oversight and it shows.
Re:OpenCV 5 Is Here: The Biggest Leap in Years for Computer ... by trklausss on Tuesday June 09, 2026 @07:16AM (#48459546)
This is what I hate about AI. Not that people use it, it's great to accelerate specific workflows, make less mistakes etc. It's just blindly trusting it and just saying "Make a post about a CV library release, make no mistakes" and calling it a day.

Where is the human creativity in writing release notes gone?

Re:OpenCV 5 Is Here: The Biggest Leap in Years for Computer ... by vdfs on Tuesday June 09, 2026 @06:23AM (#48459109)
The illustrations couldn't be any more generic-ai
Re:OpenCV 5 Is Here: The Biggest Leap in Years for Computer ... by kphorn on Tuesday June 09, 2026 @12:45PM (#48463564)
my code, my commit - ugh
Re:OpenCV 5 Is Here: The Biggest Leap in Years for Computer ... by claytongulick on Tuesday June 09, 2026 @06:53AM (#48459342)
I had to stop reading after: "This is not just another incremental release. OpenCV 5 is a major step forward."

If a human can't be bothered to write a piece, I can't be bothered to read it.

Re:OpenCV 5 Is Here: The Biggest Leap in Years for Computer ... by VulgarExigency on Tuesday June 09, 2026 @07:32AM (#48459703)
The endless deluge of AI prose really wears on the soul once you start noticing it.
Re:OpenCV 5 Is Here: The Biggest Leap in Years for Computer ... by thin_carapace on Tuesday June 09, 2026 @08:47AM (#48460417)
i initially adopted this line of thinking. after exposure to arguably valid cases like translated articles, it now seems to me that the most efficient path forward (after first noting AI prose) is to scan past all language and evaluate whether or not useful content is encoded within. theres no benefit to anyone (except those benefitting from societal atrophy) in wasting brain cycles on unnecessary verbosity, however blanket rejection necessarily involves loss of valuable information.
Re:OpenCV 5 Is Here: The Biggest Leap in Years for Computer ... by danjc on Tuesday June 09, 2026 @09:00AM (#48460544)
It's not just annoying, it's tiring
Re:OpenCV 5 Is Here: The Biggest Leap in Years for Computer ... by kphorn on Tuesday June 09, 2026 @12:47PM (#48463610)
I think the only thing that the human did was remove the emdash between the two sentence fragments and replace with a period.
Re:OpenCV 5 Is Here: The Biggest Leap in Years for Computer ... by dismantlethesun on Tuesday June 09, 2026 @02:16PM (#48465183)
I felt that this was an indication that OpenCV had finally discovered SemVer.
Re:OpenCV 5 Is Here: The Biggest Leap in Years for Computer ... by nnevatie on Tuesday June 09, 2026 @04:14AM (#48458162)
No one uses ONNXRuntime (nor the new engine in OpenCV 5) in production. For anything performance-sensitive, one would run models under TensorRT, as an example.
Re:OpenCV 5 Is Here: The Biggest Leap in Years for Computer ... by gunalx on Tuesday June 09, 2026 @04:36AM (#48458335)
Production dosent have to be performance sensitive, so devex may still outcompete the performance differences in some scenarios.
Re:OpenCV 5 Is Here: The Biggest Leap in Years for Computer ... by snovv_crash on Tuesday June 09, 2026 @04:48AM (#48458423)
Strong statement to make when I have at least 2 datapoints contradicting it, in SaaS and embedded/robotics.
Re:OpenCV 5 Is Here: The Biggest Leap in Years for Computer ... by amorroxic on Tuesday June 09, 2026 @05:04AM (#48458538)
Curious on what backs this assertion. As a counterpoint we’ve been running 200+ models in production for more than 5 years - language models, embedding, classifiers, low tens to hundred M params. Traffic in the order of 1-2M requests/day and everything is enabled by onnx with some cgo (or Rust) plumbing on top. What’s your SLA?
Re:OpenCV 5 Is Here: The Biggest Leap in Years for Computer ... by nnevatie on Tuesday June 09, 2026 @10:59AM (#48462038)
Ahh, I should have probably added some context around my hyperbole. I was referring to real-time computer vision - think of e.g. segmenting FHD/UHD video.
Re:OpenCV 5 Is Here: The Biggest Leap in Years for Computer ... by OvervCW on Tuesday June 09, 2026 @05:49AM (#48458885)
You can use ONNXRuntime with a TensorRT backend, so one does not exclude the other.
Re:OpenCV 5 Is Here: The Biggest Leap in Years for Computer ... by pzo on Tuesday June 09, 2026 @07:00AM (#48459396)
how are supposed to use TensorRT on iOS, iPadOS, Android or even Web? Production is not only cloud.
Re:OpenCV 5 Is Here: The Biggest Leap in Years for Computer ... by antonvs on Tuesday June 09, 2026 @08:02AM (#48459976)
We use this in production:

https://docs.rs/onnxruntime/latest/onnxruntime/

It’s a Rust wrapper around ONNX Runtime. We currently serve 5+ million inference requests per day for a highly performance-sensitive application, for a long list of major enterprise clients. We don’t use GPUs for inference, because it would be cost-prohibitive. We launch tens of thousands of VMs per day to run these workloads.

Re:OpenCV 5 Is Here: The Biggest Leap in Years for Computer ... by monster_truck on Tuesday June 09, 2026 @08:28AM (#48460228)
I've never understood how anyone comes into contact with it and thinks its anything more than an incredible inconvenience masked as the easy way of doing things. Given it a few good shakes for various uses and regretted the time spent each time
Re:OpenCV 5 Is Here: The Biggest Leap in Years for Computer ... by cik on Tuesday June 09, 2026 @09:16AM (#48460749)
Ummm embedded robotics is all about this. For years.
Re:OpenCV 5 Is Here: The Biggest Leap in Years for Computer ... by dTal on Tuesday June 09, 2026 @03:26PM (#48466375)
OpenTrack uses it for its AI headtracking, which works extremely well.