Christian Wolf's Avatar

Christian Wolf

@chriswolfvision.bsky.social

Principal Scientist at Naver Labs Europe, Lead of Spatial AI team. AI for Robotics, Computer Vision, Machine Learning. Austrian in France. https://chriswolfvision.github.io/www/

6,305 Followers  |  817 Following  |  2,032 Posts  |  Joined: 08.02.2024
Posts Following

Posts by Christian Wolf (@chriswolfvision.bsky.social)

Post image Post image Post image 07.03.2026 16:04 β€” πŸ‘ 2    πŸ” 0    πŸ’¬ 0    πŸ“Œ 0
Post image

Post ECCV Cycling....

07.03.2026 15:45 β€” πŸ‘ 19    πŸ” 0    πŸ’¬ 1    πŸ“Œ 0

We are not all equal...

07.03.2026 11:43 β€” πŸ‘ 6    πŸ” 0    πŸ’¬ 0    πŸ“Œ 0

Maybe we should stop calling it vibecoding and call it what it is.

Natural language programming.

05.03.2026 23:51 β€” πŸ‘ 178    πŸ” 15    πŸ’¬ 13    πŸ“Œ 6

A publication world model!

06.03.2026 18:37 β€” πŸ‘ 5    πŸ” 0    πŸ’¬ 0    πŸ“Œ 0

I wonder when we will arrive at the part where a horse becomes a senator ...

06.03.2026 18:26 β€” πŸ‘ 3    πŸ” 0    πŸ’¬ 2    πŸ“Œ 0
Post image

Jack Dorsey on how he would run a new company
From: www.wired.com/story/jack-d...

06.03.2026 18:06 β€” πŸ‘ 3    πŸ” 0    πŸ’¬ 1    πŸ“Œ 1

You don't need to go back to 1942. "Fargo" does that as well πŸ˜†. Or any recent Clint Eastwood movie where he acts himself, like "The mule" or "Gran Torino".

06.03.2026 13:44 β€” πŸ‘ 1    πŸ” 0    πŸ’¬ 0    πŸ“Œ 0
Post image Post image

Gas prices (πŸ’Ά/litre) in Munich: Feb 2 2026 vs today

06.03.2026 10:14 β€” πŸ‘ 11    πŸ” 3    πŸ’¬ 1    πŸ“Œ 1
Post image

"Authors should not use negative v-spaces to change the template layout."

The template layout:

06.03.2026 07:56 β€” πŸ‘ 26    πŸ” 5    πŸ’¬ 0    πŸ“Œ 0

You too, if you submit!

05.03.2026 21:21 β€” πŸ‘ 2    πŸ” 0    πŸ’¬ 1    πŸ“Œ 0

That's why it's given by the snake 😜

05.03.2026 20:09 β€” πŸ‘ 1    πŸ” 0    πŸ’¬ 1    πŸ“Œ 0
Post image

ECCV 2026 deadline push at @naverlabseurope.bsky.social with @dlarlus.bsky.social @weinzaepfelp.bsky.social @mbsariyildiz.bsky.social @bjoernmichele.bsky.social @vincentleroy.bsky.social @rbregier.bsky.social + + + ....

05.03.2026 20:03 β€” πŸ‘ 25    πŸ” 1    πŸ’¬ 1    πŸ“Œ 1
Post image

It's time for this picture again ...
#ECCV2026

05.03.2026 15:53 β€” πŸ‘ 32    πŸ” 3    πŸ’¬ 2    πŸ“Œ 0

J'ai eu un troisieme appel en une semaine, un de plus depuis mon poste. Je demande gentiment de ne plus appeler, et c'est bien free.

05.03.2026 12:33 β€” πŸ‘ 0    πŸ” 0    πŸ’¬ 0    πŸ“Œ 0

Thanks, I didn't know about this!

05.03.2026 08:45 β€” πŸ‘ 0    πŸ” 0    πŸ’¬ 1    πŸ“Œ 0
Post image

Additionally it also plays with the ambiguity of projective geometry. M.C. Escher would love it.

2/2

05.03.2026 07:47 β€” πŸ‘ 9    πŸ” 0    πŸ’¬ 1    πŸ“Œ 0
Post image

There is whole comic series called "L'imbattable" on this subject by French artist Pascal Jousselin. It confuses space in the scene, with space in the comic strip itself, as in your examples above.

1/2

05.03.2026 07:47 β€” πŸ‘ 8    πŸ” 0    πŸ’¬ 1    πŸ“Œ 0

I didn't even know this word exists!

05.03.2026 07:40 β€” πŸ‘ 2    πŸ” 0    πŸ’¬ 0    πŸ“Œ 0

Increasing the fonts and changing figures on one of our 2 ECCV submissions right now, since it might be on your desk. Not kidding πŸ˜‚

05.03.2026 06:55 β€” πŸ‘ 2    πŸ” 0    πŸ’¬ 0    πŸ“Œ 0
Preview
a cartoon of homer simpson holding a card ALT: a cartoon of homer simpson holding a card

This is where the comparison breaks down. Your papers are probably more like your grand parents, telling you things you don't want to hear anymore.

"SVMs perform better than neural networks"
"Binarization is an important step in computer vision"
"Global optimization and convexity is necessary"

05.03.2026 06:52 β€” πŸ‘ 5    πŸ” 1    πŸ’¬ 1    πŸ“Œ 0

Happy "at-least-we-can-eat-pizza-together-it-compensates-for-the-stress" day!

Did I get the ajdectivization hyphens right?

05.03.2026 06:42 β€” πŸ‘ 12    πŸ” 0    πŸ’¬ 2    πŸ“Œ 0

LOL, you got me!

I thought that I would get more replies on the semantics of choosing edge detection, not on its syntax ...

04.03.2026 22:37 β€” πŸ‘ 0    πŸ” 0    πŸ’¬ 0    πŸ“Œ 0

I was even considering not re-posting this old post from Twitter ... since nobody requires these hints anymore. You just ask LLM to solve your LaTeX problems πŸ˜†

04.03.2026 22:21 β€” πŸ‘ 1    πŸ” 0    πŸ’¬ 1    πŸ“Œ 0

TIL that
- "state of the art" is a noun, so we compare to the state of the art
- "state-of-the-art" is an adjective, so we can write about the state-of-the-art model on, say, edge-detection or thresholding or binarization.

04.03.2026 21:02 β€” πŸ‘ 19    πŸ” 3    πŸ’¬ 3    πŸ“Œ 1
Post image Post image

I am done with subfigure and raisebox. Placing sub figures with tikz gives me all the flexibility I need, in particular when their sizes are varying.

04.03.2026 19:55 β€” πŸ‘ 11    πŸ” 1    πŸ’¬ 1    πŸ“Œ 0

Authorship is like parenting: you love all your papers the same and you do not prefer one over the others.

04.03.2026 08:54 β€” πŸ‘ 6    πŸ” 0    πŸ’¬ 2    πŸ“Œ 1

I used the term 'reasoning' a lot in the past but then people exclusively linked it to chain of thought in LLMs and were confused with our work (came to our poster... "but this is not reasoning!").

Soon we will need to abandon the term 'agent' if it does not involve an LLM.

03.03.2026 23:19 β€” πŸ‘ 16    πŸ” 0    πŸ’¬ 2    πŸ“Œ 0

SIGBOVIK has a Bluesky now! Follow to learn more cutting-edge research from the world’s most comedic and occasionally scientific academic conference

27.02.2026 21:01 β€” πŸ‘ 64    πŸ” 25    πŸ’¬ 0    πŸ“Œ 2
Post image

Current state: ECCV

03.03.2026 15:52 β€” πŸ‘ 10    πŸ” 0    πŸ’¬ 0    πŸ“Œ 0