🚀 Just released: FLAIR – a new training-free approach to solving inverse problems using flow-matching models! 🎯 Try it live: huggingface.co/spaces/prs-e... 📚 Learn more: inverseflair.github.io Julius Erbach, Dominik Narnhofer, Andreas Dombos, Bernt Schiele, Jan Eric Lenssen, Konrad Schindler

Introducing 🛹 RollingDepth 🛹 — a universal monocular depth estimator for arbitrarily long videos! Our paper, “Video Depth without Video Models,” delivers exactly that, setting new standards in temporal consistency. Check out more details in the thread 🧵