Image Matching Challenge 2025 Ongoing Ongoing leaderboard for Image Matching Challenge 2025.

It seems, that we have failed the communication about IMC26. Let's try again.

The competition this year is here:
kaggle.com/competitions...
No prizes, but whole year leaderboard -- similar to KITTY and other academic competitions.
3D people, please retweet and share.

That's just codex. CC does not ask for a full match, I think

I wonder if that also holds for register tokens

Good ol optical flow papers, not a bad one either!

The Electric Motor and the Drill - we use AI in the wrong way Power tools are better than general purpose tools for most applications, my science planning app planyourscience.com is a result of this philosophy

In which @kordinglab.bsky.social argues LLMs are more like an electric motor than a drill, and starts to build a drill for scientific research.

open.substack.com/pub/kording/...

Thanks! Looking forward to trying it out :)

Thanks! I meant table 7 for the monocular comparison. Essentially, I wonder whether this approach (with sampling n=1) is a better approach for a monocular encoder instead of the DinoV3 objective given the same compute? Right now it's not clear to me because DinoV3 was using much more compute.

nice work!
I am somewhat surprised that MAE is worse than DinoV3 on the monocular dense benchmark. Do you have an intuition why this is the case?
Have you also tried sampling a single view instead of only 2 or more views? Mostly wondering if that has negative side-effects on the outcome.

Nice! Who wants to go outside in bad weather anyway

It's unfortunate that not open sourcing the models is the best strategy against this attack

It's interesting that this seems so controversial yet clearly it's a correct statement.

Even I’m not sure this will end well. Graphics courtesy of Dylan Patel of SemiAnalysis.

Is sky segmentation happening?

Found this near Lugano. It cannot be a coincidence.

Channel-last for everything please

Before that, the EU railway system has to be unified and fixed. Want to book a train from Zurich to Barcelona? Impossible (not a joke)

excuse me sir, could you align the y-axis?

With bad actors I mean terrorist states and organizations. They don't care. You are probably right that at least some usage in civilized parts of the world will be prevented.

Good summary of the state of social media in 2025

Bad actors read licenses?

On the neuron level that makes sense to me. Neurons are often modeled as ODEs (with feedback, though)

Iterative Residual Refinement for Joint Optical Flow and Occlusion Estimation Deep learning approaches to optical flow estimation have seen rapid progress over the recent years. One common trait of many networks is that they refine an initial flow estimate either through multip...

Though, they should have mentioned this work as well: arxiv.org/abs/1904.05290

WAFT: Warping-Alone Field Transforms for Optical Flow We introduce Warping-Alone Field Transforms (WAFT), a simple and effective method for optical flow. WAFT is similar to RAFT but replaces cost volume with high-resolution warping, achieving better accu...

For optical flow nerds: Iterative image warping strikes back

arxiv.org/abs/2506.21526

If someone complains you know that they read your thesis

Show Your Stripes Visualising how the climate has changed for every country across the globe

🫠

showyourstripes.info/c/europe/fra...

Jokes aside, I hope you get better soon!

80% dropout is still too high. You should inform your body about that

Wow that's high quality jazz!

I hope she also condemned Hamas in her speech as well as Iran. Because the truth is not Israel == evil but that hatred == evil. And there is plenty of hatred around that must be called out.

Drawing the line of autonomy too early will eventually also lead to inferior systems and make you lose a war. One could argue that more autonomy is justified to stay alive.