Kornia
Computer vision library for deep learning
Kornia launched on July 29, 2021 with 81 votes, #774 of 3,502 launches that month and more than 75% of that year's launches. The site was still online in September 2026, 5 years on.
What it does
Kornia is a differentiable computer vision library for PyTorch. It consists of a set of routines and differentiable modules to solve generic computer vision problems.
Kornia is a non-profit organisation building computer vision for robotics and spatial AI: a differentiable PyTorch library with millions of installs a month, and a Rust stack that runs the same geometry on Jetson, Raspberry Pi and any Linux device.
Kornia is a non-profit building the stack for spatial AI — from differentiable vision for research to real-time perception on robots — maintained by a small team and funded by the people who use it. Most vision projects die between the prototype and the device. This is the path the stack is built for: write the perception once, then carry it down to the hardware. Start where research starts: in PyTorch, with operators and models that gradients flow through. On the right, three of them run on a clip in your browser: YuNet finding a face, a random affine augmentation held fixed for the whole pass, and Sobel edges. Try the rest in the playground before writing a line. The prototype…from kornia.org
Does a similar job
all alternatives →
Set of trained deep learning models for computer vision2016 · github.com · ▲127Keras code and weights files for popular deep learning models. - fchollet/deep-learning-models
Torch Lens Maker – Differentiable Geometric Optics in PyTorch2025 · victorpoughon.github.io · ▲179Hello HN! For the past 6 months I've been working on an open source python library that implements differentiable geometric optics in PyTorch. It's very experimental still, but eventually the goal is to use it to design optical systems with a state of the art optimization framework and a beautiful code based API. Think OpenSCAD, but for optical systems. Not only is PyTorch's autograd an amazing general purpose optimizer, but torch.nn (the neural network building blocks) can be used pretty much out of the box to model an optical system. This is because there is a strong analogy to be made…
- ITIntroduction to Simple Computational Geometry Concepts Using C++2018 · wykobi.com · ▲114

Pythagora - automated integration tests2023 · github.com · ▲141Save 30% of dev time - generate tests without writing code
PyTorch Lightning2020 · pytorchlightning.ai · ▲79The light PyTorch wrapper for high-performance AI research
More ai this month
the category →



Paintings by AI models: programs run through a simulation of oil paint.
AI · 26d ago · stillwet.art

FastRouter.ai▲364Route requests to the right LLM for cost, latency & quality
AI · 27d ago · fastrouter.ai
Source: Product Hunt launch ↗
Launched alongside, July 2021
the whole month →
Typedream▲1,426No-code site builder, easy as Notion, pretty as Webflow
Dev tools · 2021 · typedream.com


An 8-week founder program inspired by Product Hunt
Life & fun · 2021 · hyper.com

200+ open source alternatives to popular B2B tools
Dev tools · 2021 · btw.so

Het beste casino zonder vergunning voor Nederlandse spelers kiezen? Ontdek waar je op moet letten en hoe je een betrouwbaar platform vindt dat aansluit bij jouw voorkeuren.
Life & fun · 2021 · static.wiki
