Noah Snavely

Over the past year, my lab has been working on fleshing out theory + applications of the Platonic Representation Hypothesis.

Today I want to share two new works on this topic:

Eliciting higher alignment: arxiv.org/abs/2510.02425
Unpaired learning of unified reps: arxiv.org/abs/2510.08492

1/9

#TTT3R: 3D Reconstruction as Test-Time Training
TTT3R offers a simple state update rule to enhance length generalization for #CUT3R — No fine-tuning required!
🔗Page: rover-xingyu.github.io/TTT3R
We rebuilt @taylorswift13’s "22" live at the 2013 Billboard Music Awards - in 3D!

We present a new approach to inference-time scene optimization, which we name Radiant Triangle Soup (RTS) www.arxiv.org/abs/2505.23642. Also check out really great concurrent work from Held et al. @janheld.bsky.social, Triangle Splatting arxiv.org/abs/2505.19175

🧠How “old” is your model?

Put it to the test with the KiVA Challenge: a new benchmark for abstract visual reasoning, grounded in real developmental data from children and adults.

🏆 Prizes:
🥇$1K to the top model
🥈🥉$500
📅 Deadline: 10/7/25
🔗 kiva-challenge.github.io
@iccv.bsky.social

(ChatGPT claims that this piece is Twinkle Twinkle Little Star, while Gemini says it is Do-Re-Me.)

ChatGPT and Gemini both seem to struggle with sheet music. They both insist that this excerpt is in D major (2 sharps), and resist any attempt to tell them that there 3 sharps in the key signature. I think this is really cool and interesting!

Think LMMs can reason like a 3-year-old?

Think again!

Our Kid-Inspired Visual Analogies benchmark reveals where young children still win: ey242.github.io/kiva.github....

Catch our #ICLR2025 poster today to see where models still fall short!

Thurs. April 24
3-5:30 pm
Halls 3 + 2B #312

Dynamic Camera Poses and Where to Find Them

Chris Rockwell, @jtung.bsky.social, Tsung-Yi Lin, Ming-Yu Liu, David F. Fouhey, Chen-Hsuan Lin

tl;dr: a large-scale dataset of dynamic Internet videos annotated with camera poses

arxiv.org/abs/2504.17788

1/6 🔍➡️ How to transform standard videos into immersive 360° panoramas? We've designed a new AI system for video-to-360° panorama generation!

Our key insight: large-scale data is crucial for robust panoramic synthesis across diverse scenes.

We have released the Stereo4D dataset! Explore the real-world dynamic 3D tracks: github.com/Stereo4d/ste...

This is really nice work on visual discovery from @boyangdeng.bsky.social!

We're very excited to introduce TAPNext: a model that sets a new state-of-art for Tracking Any Point in videos, by formulating the task as Next Token Prediction. For more, see: tap-next.github.io

A thread of thoughts on radiance fields, from my keynote at 3DV:

Radiance fields have had 3 distinct generations. First was NeRF: just posenc and a tiny MLP. This was slow to train but worked really well, and it was unusually compressed --- The NeRF was smaller than the images.

Fifth Ave jammed #handsoff

🚀 We’ve just released the code and checkpoints for our #ICLR2025 Oral paper: "LVSM: A Large View Synthesis Model with Minimal 3D Inductive Bias".

Check it out below 👇

🔗 Code: github.com/haian-jin/LVSM
📄 Paper: arxiv.org/abs/2410.17242
🌐 Project Page: haian-jin.github.io/projects/LVSM/

This is really cool work!

[1/10] Is scene understanding solved?

Models today can label pixels and detect objects with high accuracy. But does that mean they truly understand scenes?

Super excited to share our new paper and a new task in computer vision: Visual Jenga!

📄 arxiv.org/abs/2503.21770
🔗 visualjenga.github.io

#Backslash at #CornellTech, dedicated to advancing new works of art and technology that escape convention, has announced Mimi Ọnụọha as its first Backslash Fellow: tech.cornell.edu/news/mimi-on...

“This work feels like a marked evolution for me personally,” said Ọnụọha.

@snavely.bsky.social

Broadening Participation Scholarship Form CVPR 2025 Travel and Registration Support Application CVPR'25 is committed to supporting students from communities that do not traditionally attend CVPR through registration and travel support. Allocation is based on a combination of need, contribution to the conference, where you are traveling from, the community(ies) you identify with and advisor support. Travel support will be issued in fixed amounts that will be based on availability of funds and travel distance. If you would like to be considered for this support, please complete the following application. Decisions will be made on a rolling basis. Applications will be accepted until April 19 2025 (anywhere on earth).

#CVPR2025 offers registration and travel support to students from underrepresented communities. Awards are based on need, contribution, travel distance, identity, and advisor support.

Information and form: forms.gle/uDR2Q74drC4V...

Very nice! Is this a thing that happens each night at the hotel?

This is really bad!

Exciting news! MegaSAM code is out🔥 & the updated Shape of Motion results with MegaSAM are really impressive! A year ago I didn't think we could make any progress on these videos: shape-of-motion.github.io/results.html
Huge congrats to everyone involved and the community 🎉

Very interesting! The guy who loves singing through a megaphone comes to mind, but I think he came later.

The Dispossesed is an interesting choice! I didn't know it had a big influence.

Very interesting -- thank you!

I think Qianqian et al's work is really cool! The problem of modeling state within a 3D reasoning system is quite interesting.

(And I believe it's pronounced "cuter".)

Late to post, but excited to introduce CUT3R!

An online 3D reasoning framework for many 3D tasks directly from just RGB. For static or dynamic scenes. Video or image collections, all in one!

Project Page: cut3r.github.io
Code and Model: github.com/CUT3R/CUT3R

The thought also occurred to me that LLMs might intentionally be designed to produce slightly off-kilter text, to make it easier for whoever cares to distinguish human writing from LLM writing.

That's a great point! This case seems like such a step function to me -- I never noticed it before, now all of a sudden I see it everywhere. I asked one author, and they said that they did an LLM polishing step. But maybe I'm leaping to conclusions. Or, maybe LLMs are accelerating an existing trend.

This is really unimportant, but I keep seeing the word "advancements" in writing where I would have seen the word "advances" before.

I'm taking this to mean that LLMs are at play and therefore, they will influence the language such that the two words will eventually come to mean the same thing!