📢 NeurIPS 2025 Spotlight 📢
Can we embed motion into image representations?
FlowFeat embeds optical flow into pixel-level representations, which results in sharp feature grids, especially for dynamic objects.
Project website: tum-vision.github.io/flowfeat
With Anna Sonnweber and Daniel Cremers.
02.12.2025 18:08 — 👍 6 🔁 2 💬 0 📌 0
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
03.06.2025 09:27 — 👍 27 🔁 12 💬 1 📌 0
📢 #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
04.04.2025 13:38 — 👍 22 🔁 6 💬 1 📌 2
“After carefully reading the other reviews and the author response, I keep my score ‘borderline’” 😣
#CVPR2025
04.02.2025 18:20 — 👍 4 🔁 0 💬 0 📌 0
My group is looking for motivated PhD students that want to work on the future of digital humans.
Within the ERC project 'LeMo: Learning Digital Humans in Motion' there are two open positions:
www.career.tu-darmstadt.de/HPv3.Jobs/TU...
www.career.tu-darmstadt.de/HPv3.Jobs/TU...
14.01.2025 19:07 — 👍 20 🔁 7 💬 0 📌 0
ELIZA is a Konrad Zuse Schools of Excellence in Artificial Intelligence funded by @daadworldwide.bsky.social. We train #AItalents building on @ellis.eu. #ZuseSchoolsAI
Follow us on: eliza.school
Explore the latest AI research trends and meet others in the field at ResearchTrend.AI.
https://researchtrend.ai/
ericzzj1989.github.io
PhD from CUHK. 3D vision, SLAM, SfM, Image Matching (https://github.com/ericzzj1989/Awesome-Image-Matching).
PhD student at the University of Tuebingen. Computer vision, video understanding, multimodal learning.
https://ninatu.github.io/
Postdoctoral researcher at the computer vision group TUM
@tumuenchen.bsky.social
Lead by Prof. @thomasbrox.bsky.social
https://lmb.informatik.uni-freiburg.de/
ML Researcher, Qualcomm AI Research
Postdoc, University of British Columbia
Vector Institute
PhD, TU Darmstadt
Postdoc at Visual Inference Lab, TU Darmstadt
European Research Council, set up by the EU, funds top researchers of any nationality, helping them pursue great ideas at the frontiers of knowledge. #HorizonEU
Ph.D. student at the computer vision group TUM @tumuenchen.bsky.social
Supervised by Prof.Cremers @dcremers.bsky.social
https://sangluisme.github.io
Professor in Scalable Trustworthy AI @ University of Tübingen | Advisor at Parameter Lab & ResearchTrend.AI
https://seongjoonoh.com | https://scalabletrustworthyai.github.io/ | https://researchtrend.ai/
Computer Vision research group @ox.ac.uk
Associate Professor & Co-Founder - Dynamical Deep Learning
Probabilistic ML researcher at Google Deepmind
Assistant Professor for 3D Computer Vision at University of Amsterdam.
3D Human-centric Perception & Synthesis: bodies, hands, objects.
Past: MPI for Intelligent Systems, Univ. of Bonn, Aristotle Univ. of Thessaloniki
Website: https://dtzionas.com
#CS Associate Prof York University, #ComputerVision Scientist Samsung #AI, VectorInst Faculty Affiliate, TPAMI AE, ELLIS4Europe Member, #CVPR2026 #ECCV2026 Publicity Chair
📍Toronto 🇨🇦 🔗 csprofkgd.github.io
🗓️ Joined Nov 2024
Research Scientist at valeo.ai | Teaching at Polytechnique, ENS | Alumni at Mines Paris, Inria, ENS | AI for Autonomous Driving, Computer Vision, Machine Learning | Robotics amateur
⚲ Paris, France 🔗 abursuc.github.io
https://Answer.AI & https://fast.ai founding CEO; previous: hon professor @ UQ; leader of masks4all; founding CEO Enlitic; founding president Kaggle; various other stuff…
www.dgp.toronto.edu/~hertzman
