Johan Edstedt
@parskatt.bsky.social
PhD student @ Linköping University
I like 3D vision and training neural networks.
Code: https://github.com/parskatt
Weights: https://github.com/Parskatt/storage/releases/tag/roma
I like 3D vision and training neural networks.
Code: https://github.com/parskatt
Weights: https://github.com/Parskatt/storage/releases/tag/roma
Accepted to #3DV2026!
Radially Distorted Homographies, Revisited
Mårten Wadenbäck, Marcus Valtonen Örnhag, @parskatt.bsky.social
tl;dr: minimal solvers for one-sided/two-sided equal/two-sided independent radial distortion homography
arxiv.org/abs/2508.21190
Mårten Wadenbäck, Marcus Valtonen Örnhag, @parskatt.bsky.social
tl;dr: minimal solvers for one-sided/two-sided equal/two-sided independent radial distortion homography
arxiv.org/abs/2508.21190
November 7, 2025 at 7:47 AM
Accepted to #3DV2026!
I don't want to submit to any conference that would accept my paper.
November 6, 2025 at 12:51 PM
I don't want to submit to any conference that would accept my paper.
CVPR compute form is so incredibly dumb.
November 6, 2025 at 8:16 AM
CVPR compute form is so incredibly dumb.
Did everyone get this?
November 4, 2025 at 8:41 AM
Did everyone get this?
why is this so true
AGI is when models write good multi-dim torch indexing code.
October 29, 2025 at 9:16 AM
why is this so true
I just put `MultiScaleDeformableAttention` wheels on pypi under `ms-deform-attn`.
Should make stuff involving mask2former a bit smoother.
Should make stuff involving mask2former a bit smoother.
October 21, 2025 at 7:31 PM
I just put `MultiScaleDeformableAttention` wheels on pypi under `ms-deform-attn`.
Should make stuff involving mask2former a bit smoother.
Should make stuff involving mask2former a bit smoother.
Gonna start using this
October 21, 2025 at 7:14 AM
Gonna start using this
Pro-tip: Set the loss range in your wandb plot unreasonably low to motivate your models to try harder.
October 20, 2025 at 2:09 PM
Pro-tip: Set the loss range in your wandb plot unreasonably low to motivate your models to try harder.
AGI is when models write good multi-dim torch indexing code.
October 16, 2025 at 8:12 PM
AGI is when models write good multi-dim torch indexing code.
Cursor tab likes to sprinkle in some "delete 20 lines of code" seemingly at random.
I like that it adds a bit of excitement to the coding experience.
I like that it adds a bit of excitement to the coding experience.
October 16, 2025 at 5:30 PM
Cursor tab likes to sprinkle in some "delete 20 lines of code" seemingly at random.
I like that it adds a bit of excitement to the coding experience.
I like that it adds a bit of excitement to the coding experience.
Spooky features
Pro tip: For good Halloween vibes, use non-normalized RoPE on images larger than your training resolution and larger than the composite period of some of the RoPE-rotations. You might get scary ghost structures in your features.
October 16, 2025 at 3:10 PM
Spooky features
Sweden is a Monarchy that functions like a Democracy.
Some other countries do it the other way round.
Must say I prefer the former.
Some other countries do it the other way round.
Must say I prefer the former.
October 16, 2025 at 10:52 AM
Sweden is a Monarchy that functions like a Democracy.
Some other countries do it the other way round.
Must say I prefer the former.
Some other countries do it the other way round.
Must say I prefer the former.
All papers I was assigned for 3DV were significantly higher quality than the papers I was assigned for ICCV.
October 10, 2025 at 7:38 AM
All papers I was assigned for 3DV were significantly higher quality than the papers I was assigned for ICCV.
Yesterday I (successfully) defended my doctoral thesis 🎉
You are now forced to call me Dr. Edstedt.
You are now forced to call me Dr. Edstedt.
Public defence of doctoral thesis in Electrical Engineering - Johan Edstedt
Johan Edstedt, at the Department of Electrical Engineering (ISY), defends his doctoral thesis "Towards the Next Generation of 3D Reconstruction”. Opponent…
vimeo.com
October 9, 2025 at 9:16 PM
Yesterday I (successfully) defended my doctoral thesis 🎉
You are now forced to call me Dr. Edstedt.
You are now forced to call me Dr. Edstedt.
Worth going!
The Visual Recognition Group at CTU in Prague organizes the 50th Pattern Recognition and Computer Vision Colloquium with
Torsten Sattler, Paul-Edouard Sarlin, Vicky Kalogeiton, Spyros Gidaris, Anna Kukleva, and Lukas Neumann.
On Thursday Oct 9, 11:00-17:00.
cmp.felk.cvut.cz/colloquium/
Torsten Sattler, Paul-Edouard Sarlin, Vicky Kalogeiton, Spyros Gidaris, Anna Kukleva, and Lukas Neumann.
On Thursday Oct 9, 11:00-17:00.
cmp.felk.cvut.cz/colloquium/
October 6, 2025 at 4:08 PM
Worth going!
Hinton, the random plumber of AI
Why are you citing someone from a completely unrelated field as a source. You might as well source some random plumber.
October 6, 2025 at 12:34 PM
Hinton, the random plumber of AI
Went to Carolina Revidiva in Uppsala to see Carta Marina (my thesis cover) in person
October 4, 2025 at 11:21 AM
Went to Carolina Revidiva in Uppsala to see Carta Marina (my thesis cover) in person
I'd like to reiterate this point, but even for outputs with 3 or less channels (xyz, depth, warps, etc).
What you end up selecting for is aesthetic appeal, although that might be good for getting papers accepted...
What you end up selecting for is aesthetic appeal, although that might be good for getting papers accepted...
Slightly obvious take:
Good features have more than 3 active PCs per image. You can't really judge whether they're good by visual inspection (unless you have really good hyperspectral vision).
Good features have more than 3 active PCs per image. You can't really judge whether they're good by visual inspection (unless you have really good hyperspectral vision).
October 3, 2025 at 5:40 PM
I'd like to reiterate this point, but even for outputs with 3 or less channels (xyz, depth, warps, etc).
What you end up selecting for is aesthetic appeal, although that might be good for getting papers accepted...
What you end up selecting for is aesthetic appeal, although that might be good for getting papers accepted...
Architecture search from scratch is terrifying.
Search space is basically infinite, and any of your choices could cripple the model.
Search space is basically infinite, and any of your choices could cripple the model.
October 3, 2025 at 1:44 PM
Architecture search from scratch is terrifying.
Search space is basically infinite, and any of your choices could cripple the model.
Search space is basically infinite, and any of your choices could cripple the model.
Happy to share that I've been recognized as one of the "Above Mediocre Reviewers" for ICCV 2025!
bsky.app/profile/iccv...
bsky.app/profile/iccv...
Happy to share that I've been recognized as one of the "Mediocre Reviewers" for CVPR 2025!
Behind every great conference is a team of dedicated reviewers. Congratulations to this year’s #CVPR2025 Outstanding Reviewers!
cvpr.thecvf.com/Conferences/...
cvpr.thecvf.com/Conferences/...
October 2, 2025 at 8:02 PM
Happy to share that I've been recognized as one of the "Above Mediocre Reviewers" for ICCV 2025!
bsky.app/profile/iccv...
bsky.app/profile/iccv...