Aligning multi-view scans
AssigneeAdobe Systems Incorporated
InventorsNathan A. Carr, Zhili Chen, Byungmoon Kim, Linjie Luo
Life of this patent
Estimating the term…
Abstract
Alignment techniques are described that automatically align multiple scans of an object obtained from different perspectives. Instead of relying solely on errors in local feature matching between a pair of scans to identify a best possible alignment, additional alignment possibilities may be considered. Grouped keypoint features of the pair of scans may be compared to keypoint features of an additional scan to determine an error between the respective keypoint features. Various alignment techniques may utilize the error to determine an optimal alignment for the scans.
Claims20
A method implemented by a computing device, the method comprising:
- forming a partial alignment for a plurality of scans of an object obtained from different perspectives including:
- recognizing keypoint features within the plurality of scans;
- assigning error values to potential matches between keypoint features of the plurality of scans;
- matching two or more keypoint features using the assigned error values to produce the partial alignment;
- computing an error associated with combining the partial alignment with one or more additional keypoint features;
- and
- determining whether to accept or reject the partial alignment based upon comparison of the computed error to a threshold established to prune potential alignments.
A system comprising:
- a processor;
- and
- a memory, storing instructions that, responsive to execution by the processor, configures the processor to:
- form a partial alignment for a plurality of scans of an object obtained from different perspectives by an image capturing device, to form the partial alignment including:
- recognize keypoint features within the plurality of scans;
- assign an error value to a potential match between keypoint features of the plurality of scans;
- match two or more keypoint features using the assigned error value to produce the partial alignment;
- compute an error associated with combining the partial alignment with one or more additional keypoint features;
- and
- determine whether to accept or reject the partial alignment based upon comparison of the computed error to a threshold established to prune potential alignments.
One or more non-transitory computer-readable storage media storing instructions that, responsive to execution by a computing device, cause the computing device to perform operations to produce a three-dimensional (3D) model representation of an object, the operations comprising:
- assigning error values to potential matches between keypoint features of a pair of scans, each potential match representing a different partial alignment of matched keypoint features corresponding to the pair of scans;
- selecting a partial alignment for further processing based on the assigned errors;
- computing an error associated with combining the selected partial alignment with one or more additional keypoint features of another scan;
- and
- determining whether to accept or reject the selected partial alignment based upon comparison of the computed error to a threshold established to prune potential alignments.
Dependencies are inferred from the claim text.