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 and monocular SLAM techniques assume input videos that feature predominantly static scenes with large...

Full description

Saved in:
Bibliographic Details
Published in:arXiv.org 2024-12
Main Authors: Li, Zhengqi, Tucker, Richard, rester, Cole, Wang, Qianqian, Jin, Linyi, Ye, Vickie, Kanazawa, Angjoo, Holynski, Aleksander, Snavely, Noah
Format: Article
Language:English
Subjects:
Cameras
Field of view
Interactive systems
Motion perception
Neural networks
Parallax
Parameter estimation
Parameter modification
Parameter robustness
Robustness
Video
Visual fields
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary: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 and monocular SLAM techniques assume input videos that feature predominantly static scenes with large amounts of parallax. Such methods tend to produce erroneous estimates in the absence of these conditions. Recent neural network-based approaches attempt to overcome these challenges; however, such methods are either computationally expensive or brittle when run on dynamic videos with uncontrolled camera motion or unknown field of view. We demonstrate the surprising effectiveness of a deep visual SLAM framework: with careful modifications to its training and inference schemes, this system can scale to real-world videos of complex dynamic scenes with unconstrained camera paths, including videos with little camera parallax. Extensive experiments on both synthetic and real videos demonstrate that our system is significantly more accurate and robust at camera pose and depth estimation when compared with prior and concurrent work, with faster or comparable running times. See interactive results on our project page: https://mega-sam.github.io/
ISSN:2331-8422