Interested in 3D DINO features from a single image or unsupervised scene understanding?🦖
Come by our SceneDINO poster at NeuSLAM today 14:15 (Kamehameha II) or Tue, 15:15 (Ex. Hall I 627)!
W/ Jevtić @fwimbauer.bsky.social @olvrhhn.bsky.social Rupprecht, @stefanroth.bsky.social @dcremers.bsky.social
New opening for Assistant Professor in Machine Learning at Cambridge @eng.cam.ac.uk closing on 22 Sept 2025:
www.jobs.cam.ac.uk/job/49361/
The code for our #CVPR2025 paper, PRaDA: Projective Radial Distortion Averaging, is now out!
Turns out distortion calibration from multiview 2D correspondences can be fully decoupled from 3D reconstruction, greatly simplifying the problem
arxiv.org/abs/2504.16499
github.com/DaniilSinits...
🦖 We present “Feed-Forward SceneDINO for Unsupervised Semantic Scene Completion”. #ICCV2025
🌍: visinf.github.io/scenedino/
📃: arxiv.org/abs/2507.06230
🤗: huggingface.co/spaces/jev-a...
@jev-aleks.bsky.social @fwimbauer.bsky.social @olvrhhn.bsky.social @stefanroth.bsky.social @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
We have a PhD opening in Berlin on "Responsible Data Engineering", with a focus on data preparation for ML/AI systems.
This is a fully-funded position with salary level E13 at the newly founded DEEM Lab, as part of @bifold.berlin .
Details available at deem.berlin#jobs-2225
Can you train a model for pose estimation directly on casual videos without supervision?
Turns out you can!
In our #CVPR2025 paper AnyCam, we directly train on YouTube videos and achieve SOTA results by using an uncertainty-based flow loss and monocular priors!
⬇️
Happy to be recognized as an Outstanding Reviewer at #CVPR2025 🎊
While recent methods like Monst3r achieve impressive results, they require datasets with camera pose labels. Such datasets are hard to collect and not available for every domain. AnyCam can directly be trained on any video dataset.
More details: fwmb.github.io/anycam
Can you train a model for pose estimation directly on casual videos without supervision?
Turns out you can!
In our #CVPR2025 paper AnyCam, we directly train on YouTube videos and achieve SOTA results by using an uncertainty-based flow loss and monocular priors!
⬇️
📢 #CVPR2025 Highlight: Scene-Centric Unsupervised Panoptic Segmentation 🔥
We present CUPS, the first unsupervised panoptic segmentation method trained directly on scene-centric imagery.
Using self-supervised features, depth & motion, we achieve SotA results!
🌎 visinf.github.io/cups
🏠 Introducing DepthSplat: a framework that connects Gaussian splatting with single- and multi-view depth estimation. This enables robust depth modeling and high-quality view synthesis with state-of-the-art results on ScanNet, RealEstate10K, and DL3DV.
🔗 haofeixu.github.io/depthsplat/
🤗 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
Announcing the 2025 NAVSIM Challenge! What's new? We're testing not only on real recordings—but also imaginary futures generated from the real ones! 🤯
Two rounds: #CVPR2025 and #ICCV2025. $18K in prizes + several $1.5k travel grants. Submit in May for Round 1! opendrivelab.com/challenge2025/ 🧵👇
Can we represent fuzzy geometry with meshes? "Volumetric Surfaces" uses layered meshes to represent the look of hair, fur & more without the splatting/volume overhead. Fast, pretty, and runs in real-time on your laptop!
🔗 autonomousvision.github.io/volsurfs/
📄 arxiv.org/pdf/2409.02482
ArXiV: arxiv.org/abs/2503.23282
Code and models: github.com/Brummi/anycam
Project page: fwmb.github.io/anycam/
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
Screenshot of the workshop website "Emergent Visual Abilities and Limits of Foundation Models" at CVPR 2025
Our paper submission deadline for the EVAL-FoMo workshop @cvprconference.bsky.social has been extended to March 19th!
sites.google.com/view/eval-fo...
We welcome submissions (incl. published papers) on the analysis of emerging capabilities / limits in visual foundation models. #CVPR2025
Check out the recent CVG papers at #CVPR2025, including our (@olvrhhn.bsky.social, @neekans.bsky.social, @dcremers.bsky.social, Christian Rupprecht, and @stefanroth.bsky.social) work on unsupervised panoptic segmentation. The paper will soon be available on arXiv. 🚀
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
Tomorrow in our TUM AI - Lecture Series with none other than Robin Rombach, CEO Black Forest Labs.
He'll talk about "𝐅𝐋𝐔𝐗: Flow Matching for Content Creation at Scale".
Live stream: youtube.com/live/nrKKLJX...
6pm GMT+1 / 9am PST (Mon Feb 17rd)
Our 2nd Workshop on Emergent Visual Abilities and Limits of Foundation Models (EVAL-FoMo) is accepting submissions. We are looking forward to talks by our amazing speakers that include @saining.bsky.social, @aidanematzadeh.bsky.social, @lisadunlap.bsky.social, and @yukimasano.bsky.social. #CVPR2025
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
🏔️⛷️ Looking back on a fantastic week full of talks, research discussions, and skiing in the Austrian mountains!
🥳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
This week we had our winter retreat jointly with Daniel Cremer's group in Montafon, Austria. 46 talks, 100 Km of slopes and night sledding with some occasionally lost and found. It has been fun!
Indeed - everyone had a blast - thank you all for the great talks, discussions and Ski/snowboarding!
