Opt-keyframe reconstruction for robust video-based structure from motion

摘要

An opt-keyframe reconstruction technique for selecting and reconstructing optimizing keyframes to provide a better reconstruction in a structure from motion (SFM) technique. The technique may, for example, be used in an adaptive reconstruction algorithm implemented by a general SFM technique. This technique may add and reconstruct optimizing frames to a set of keyframes already generated by an initialization technique and by an adaptive technique for iteratively selecting and reconstructing additional keyframes. In addition, the technique may determine and remove outlier points from the projection, and determine and recover inlier points in the projection. Adding the opt-keyframes and inlier points may result in additional, and possibly shorter, point trajectories being included in the reconstruction, thus providing a better reconstruction that may be more suited for later operations that may be applied to the image sequence.

主权项

1. A method, comprising:
performing, by one or more computing devices:
obtaining a reconstruction of camera motion and camera intrinsic parameters for an image sequence including a plurality of frames, the reconstruction including a set of keyframes selected from the plurality of frames of the image sequence;selecting a frame not included in the reconstruction and between keyframes in the reconstruction;reconstructing camera motion and camera intrinsic parameters for the selected frame according to the reconstruction and at least a portion of a set of point trajectories for the image sequence, the reconstructing adding the selected frame to the reconstruction; andrepeating the selecting and the reconstructing until a total number of frames included in the reconstruction reaches a specified threshold.