MegaSaM: Accurate, Fast and Robust Structure and Motion from Casual Dynamic Videos We present a system that allows for accurate, fast, and robust estimation of camera parameters and depth maps from casual monocular videos of dynamic scenes. Most conventional structure from motion an...

🔗See the gallery of results, and try our interactive viewer at mega-sam.github.io
📄Read more: arxiv.org/abs/2412.04463

Big thanks to the amazing team! @holynski.bsky.social, @snavely.bsky.social, Richard Tucker, Forrester Cole, Qianqian Wang, Linyi Jin, Vickie Ye, Angjoo Kanazawa

06.12.2024 17:42 — 👍 11    🔁 1    💬 1    📌 0

Introducing MegaSaM!

Accurate, fast, & robust structure + camera estimation from casual monocular videos of dynamic scenes!

MegaSaM outputs camera parameters and consistent video depth, scaling to long videos with unconstrained camera paths and complex scene dynamics!

06.12.2024 17:42 — 👍 69    🔁 18    💬 1    📌 4