Daniel Cremers

🤗 I’m excited to share our recent work: TwoSquared: 4D Reconstruction from 2D Image Pairs.
🔥 Our method produces geometry, texture-consistent, and physically plausible 4D reconstructions
📰 Check our project page sangluisme.github.io/TwoSquared/
❤️ @ricmarin.bsky.social @dcremers.bsky.social

Standard graph neural networks assign vastly different latent embeddings to graphs describing the same physical system at different resolution scales. This precludes consistency in applications and prevents generalization between scales as would fundamentally be needed in many scientific applications. We uncover the underlying obstruction, investigate its origin and show how to overcome it.

The ICLR 2025 MLMP Best Paper Award, along with 2k GPU-hours from Nebius, goes to "On Incorporating Scale into Graph Networks"! Congratulations, Christian Koke, Yuesong Shen,
@abhi-rf.bsky.social, Marvin Eisenberger, @pseudomanifold.topology.rocks, Michael M. Bronstein, @dcremers.bsky.social!

Can we match vision and language representations without any supervision or paired data?

Surprisingly, yes! 

Our #CVPR2025 paper with @neekans.bsky.social and @dcremers.bsky.social shows that the pairwise distances in both modalities are often enough to find correspondences.

⬇️ 1/4

Insights on the ELLIS Program Workshop on Machine Learning and Computer Vision The ELLIS mission is to create a diverse European network that promotes research excellence and advances breakthroughs in AI, as well as a pan-European PhD program to educate the next generation of AI...

💡Explore the insights from the ELLIS ML & Computer Vision Workshop (Apr 1-4, 2025) in Bad Teinach 🌲

Leading researchers of the field gathered to explore Vision-Language Models, 3D reconstruction, and links to neuroscience - advancing the future of vision & ML.

👉 Read more: ellis.eu/news/insight...

Very glad to announce that our "Finsler Multi-Dimensional Scaling" paper, accepted at #CVPR2025, is now on Arxiv! arxiv.org/abs/2503.18010

Check out our latest recent #CVPR2025 paper AnyCam, a fast method for pose estimation in casual videos!

1️⃣ Can be directly trained on casual videos without the need for 3D annotation.
2️⃣ Based around a feed-forward transformer and light-weight refinement.

Code and more info: ⏩ fwmb.github.io/anycam/

AnyCam: Learning to Recover Camera Poses and Intrinsics from Casual Videos

@fwimbauer.bsky.social, Weirong Chen, Dominik Muhle, Christian Rupprecht, @dcremers.bsky.social

tl;dr: uncertaintybased loss+pre-trained depth and flow networks+test-time trajectory refinement

arxiv.org/abs/2503.23282

Work by: @olvrhhn.bsky.social *, @christophreich.bsky.social *, @neekans.bsky.social, @dcremers.bsky.social, Christian Rupprecht, and @stefanroth.bsky.social

Paper: arxiv.org/abs/2504.01955
Project Page: visinf.github.io/cups
Code: github.com/visinf/cups
MCML Blogpost: mcml.ai/news/2025-04...

Back on Track: Bundle Adjustment for Dynamic Scene Reconstruction

Weirong Chen, @ganlinzhang.xyz, @fwimbauer.bsky.social, Rui Wang, @neekans.bsky.social, Andrea Vedaldi, @dcremers.bsky.social

tl;dr: learning-based 3D point tracker decouples camera and object-based motion

arxiv.org/abs/2504.14516

PRaDA: Projective Radial Distortion Averaging

Daniil Sinitsyn, @linushn.bsky.social, @dcremers.bsky.social

tl;dr: operate in Projective space->geometry is unique up to a homography

arxiv.org/abs/2504.16499

I am practising the guitar every night. 😉

We are thrilled to have 12 papers accepted to #CVPR2025. Thanks to all our students and collaborators for this great achievement!
For more details check out cvg.cit.tum.de

🚀 Excited to kick off our @iclr-conf.bsky.social 2025 Machine Learning Multiscale Processes Workshop contributed paper series! 🥳

📝 On the Successful Incorporation of Scale into Graph Neural Networks

📅 Join us on April 27 at #ICLR2025!
⏳ Early reg. deadline: March 15

#AI #ML #ICLR

🥳 Thrilled to announce that our work, "4Deform: Neural Surface Deformation for Robust Shape Interpolation," has been accepted to #CVPR2025 🙌
💻 Check our project page: 4deform.github.io
👏 Great thanks to my amazing co-authors. @ricmarin.bsky.social @dongliangcao.bsky.social @dcremers.bsky.social

Exciting discussions on the future of AI at the Paris AI Action Summit with French Minister of Science Philippe Baptiste and many leading AI researchers

Including commentary from @claireve.bsky.social, @dcremers.bsky.social, Yair Weiss, @gulvarol.bsky.social, Bernhard Schölkopf, and @lawrennd.bsky.social

🥳Thrilled to share our work, "Implicit Neural Surface Deformation with Explicit Velocity Fields", accepted at #ICLR2025 👏
code is available at: github.com/Sangluisme/I...
😊Huge thanks to my amazing co-authors. @dongliangcao.bsky.social @dcremers.bsky.social
👏Special thanks to @ricmarin.bsky.social

Hi Zubair, could you add me to your starter pack? I work on vision and robotics. Thx!

Hi Kosta, looks great! Any chance that you can add me to these starter packs?

Indeed - everyone had a blast - thank you all for the great talks, discussions and Ski/snowboarding!