Alexandre Morgand (@Almorgand)

2025-04-24 | ❤️ 188 | 🔁 26

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

TL;DR: fast transformer-based model for camera parameters; feed-forward; from diverse, unlabeled YouTube videos; uncertainty-based loss and pre-trained depth/flow networks; no direct motion supervision https://x.com/Almorgand/status/1915348413681483781/video/1