Structure from Motion for Panorama-Style Videos
Chris Sweeney, Aleksander Holynski, Brian Curless, Steve M Seitz

TL;DR
This paper introduces a new Structure from Motion pipeline tailored for panorama-style videos that accurately reconstructs camera poses without prior calibration, leveraging spherical motion assumptions and novel pose estimation methods.
Contribution
The authors develop three novel relative pose algorithms for spherical motion and incorporate a soft prior in bundle adjustment, enabling accurate reconstruction without well-triangulated points.
Findings
Accurate camera pose estimation on synthetic and real data
Effective reconstruction for panorama-style videos
Robust initialization for bundle adjustment
Abstract
We present a novel Structure from Motion pipeline that is capable of reconstructing accurate camera poses for panorama-style video capture without prior camera intrinsic calibration. While panorama-style capture is common and convenient, previous reconstruction methods fail to obtain accurate reconstructions due to the rotation-dominant motion and small baseline between views. Our method is built on the assumption that the camera motion approximately corresponds to motion on a sphere, and we introduce three novel relative pose methods to estimate the fundamental matrix and camera distortion for spherical motion. These solvers are efficient and robust, and provide an excellent initialization for bundle adjustment. A soft prior on the camera poses is used to discourage large deviations from the spherical motion assumption when performing bundle adjustment, which allows cameras to remain…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsAdvanced Vision and Imaging · Optical measurement and interference techniques · Robotics and Sensor-Based Localization
