Advancing Computer Vision & Spatial AI, openly #computervision #opensource #AI
BCN -- worldwide 🌠😎
Joined November 2019
- Tweets1.2K
- Following2K
- Followers4.9K
- Likes1.4K
Pinned Tweet
Meet kornia==0.9.0 - more correct, much faster, more documented, better half-precision, CUDA and MPS support.
More than 800 issues have been raised and fixed.
Some ops are now 2000x faster.
Others not crash :)
Way better docs. Check the release post
github.com/kornia/kornia/rel…
Kornia retweeted
Meet kornia==0.9.0 - more correct, much faster, more documented, better half-precision, CUDA and MPS support.
More than 800 issues have been raised and fixed.
Some ops are now 2000x faster.
Others not crash :)
Way better docs. Check the release post
github.com/kornia/kornia/rel…
Kornia retweeted
So, what’s new in kornia 0.9.0?
First, the conventions page - what are images, what is the channel order, arrays, coordinates, angles.
We also this information in the docstrings, so you or your agent always know.
kornia.readthedocs.io/en/sta…
So, what’s new in kornia 0.9.0?
First, the conventions page - what are images, what is the channel order, arrays, coordinates, angles.
We also this information in the docstrings, so you or your agent always know.
kornia.readthedocs.io/en/sta…
From now on, instead of question “How does AI help?” we ask “Which part was done by human, if any?”
github.com/kornia/kornia/pul…
Kornia retweeted
kornia-slam pipeline has been a huge help for all the slam work I've been doing. Really worth checking them out. I'm planning on contributing the work ive done so far to the!
Our new #rust kornia-slam pipeline is finally ou.
Check the site for more details: kornia.org/slam/
It’s fully #opensource — we are looking for battle testing users and contributors to improve it. Feel free to reach out to us !
Our new #rust kornia-slam pipeline is finally ou.
Check the site for more details: kornia.org/slam/
It’s fully #opensource — we are looking for battle testing users and contributors to improve it. Feel free to reach out to us !
Kornia retweeted
Attention arXiv authors. Because of the exponential increase in submissions, arXiv is limiting the number of papers that a person can submit each month to two. 1/
arXiv has updated our policy on rate limiting for all submitters.
This update was made to fairly distribute moderator time & support the arXiv community of staff, volunteers, readers & authors.
Please read our announcement to learn more: blog.arxiv.org/2026/10/01/up…
ALT arXiv logo in white over a whiteboard with math symbols.
New calibration functionality in #rust in real action 🚀
Next up, something I haven't REALLY managed to get working for a long time is synchronized, uncalibrated videos for person tracking.
Whenever I used something like vggt, there was just enough residual error that it didn't work and gave crap results.
I have a version now in @rerundotio that takes time-synced, but uncalibrated sparse videos -> calibrated, gravity-aligned videos within a reasonable error.
Yellow cameras are basically the naive vggt cameras (actually g3t in this case), and blue ones are after running the optimization post-processing pipeline. @kornia_foss has been shipping some cool stuff recently; in particular, they have an easy-to-use bundle adjustment pipeline in rust with kornia-rs. I was trying to use pycolmap but I kept having issues with it so it was a really nice alternative.
I'm going to be pumping out more huggingface @Gradio spaces soon so this will be the next one 🫡
Fable has gotten really good at making images. its a TLDR on how it works
Kornia retweeted
Next up, something I haven't REALLY managed to get working for a long time is synchronized, uncalibrated videos for person tracking.
Whenever I used something like vggt, there was just enough residual error that it didn't work and gave crap results.
I have a version now in @rerundotio that takes time-synced, but uncalibrated sparse videos -> calibrated, gravity-aligned videos within a reasonable error.
Yellow cameras are basically the naive vggt cameras (actually g3t in this case), and blue ones are after running the optimization post-processing pipeline. @kornia_foss has been shipping some cool stuff recently; in particular, they have an easy-to-use bundle adjustment pipeline in rust with kornia-rs. I was trying to use pycolmap but I kept having issues with it so it was a really nice alternative.
I'm going to be pumping out more huggingface @Gradio spaces soon so this will be the next one 🫡
Fable has gotten really good at making images. its a TLDR on how it works
Alright, I went ahead and built 4DAnyone into a proper @Gradio space. I thought it was cool enough that it deserved the effort and made sure to take advantage of our @rerundotio Gradio integration.
TLDR takes in a single video and is able to output multiview consistent videos. Its kinda incredible how good the quality is. Got it working on my 5090 + DGX Spark, so it works with <32GB cards =]
Sadly, I had to make this version only output 6 videos; otherwise, it would take way too long, but its able to go all the way up to 48 videos locally. Just takes like ~20-30 minutes.
No splatting on this one, as again it would just take too much GPU time that ZeroGPU won't easily support and will eat up all your quota
This also feels like the perfect fit for a new Gradio Workflow, something I'll look into at some point.
Inference time ~5-8 minutes on the space, sped things up in the video to keep it digestible
We have changed our AI and contribution policy. Now both are simple:
We ask you to care. We promise our best, but do not guarantee review for every PR.
We are using AI, so may you -just honestly say if the code/text is agent written or human written.
github.com/kornia/kornia/blo…
TorchMorph - new library in Pytorch ecosystem
Kai Zhao
Better, than kornia in everything for morphology, but requires CUDA compile.
Welcome, colleagues!
arxiv.org/abs/2608.24738
intcomp.github.io/tm/
Kornia retweeted
#kornia used for the data augmentation
The Overlooked Value of Test-time Reference Sets in Visual Place Recognition
Mubariz Zaffar, Liangliang Nan, Sebastian Scherer, Julian F. P. Kooij
tl;dr: if you have db (reference) images for VPR, finetune your model on it.
arxiv.org/abs/2510.03751
#kornia used for the data augmentation
The Overlooked Value of Test-time Reference Sets in Visual Place Recognition
Mubariz Zaffar, Liangliang Nan, Sebastian Scherer, Julian F. P. Kooij
tl;dr: if you have db (reference) images for VPR, finetune your model on it.
arxiv.org/abs/2510.03751
🚀 Welcome to the first #kornia virtual Performance Optimization Hackathon!
🗓 Dates: now – August 10, 2025 (AoE)
🏆 Prize Pool: Nintendo Switch 2 for Grand Prize Winner
🤝 Sponsored By: @codeflashAI
🧠 Hosted By: @kornia_foss
You can still register
docs.google.com/forms/d/e/1F…
Kornia retweeted
Hey #opensource maintainers, we are trying to find some tools for #github to detect and score AI generated code in our repositories in @kornia_foss. Anyone knows or has experienced with any tool ?