公开(公告)号：US20240362802A1

公开(公告)日：2024-10-31

申请号：US18306682

申请日：2023-04-25

Applicant: Microsoft Technology Licensing, LLC

Inventor： Michael BLEYER ,  Pascal PARÉ ,  Paul LEE ,  Aleksander Bogdan BAPST

IPC: G06T7/33 ,  G06T7/246 ,  G06T19/20

CPC classification number: G06T7/344 ,  G06T7/251 ,  G06T19/20 ,  G06T2219/2004 ,  G06T2219/2016 ,  H04N23/54

Abstract: A system determining motion models for aligning scene content captured by different image sensors is configurable to access a first motion model generated based upon a set of feature correspondences that includes (i) an inlier set used to determine model parameters for the first motion model and (ii) an outlier set. The system is also configurable to define a modified set of feature correspondences that includes the outlier set from the set of feature correspondences. The system is also configurable to generate a second motion model by using the modified set of feature correspondences to determine model parameters for the second motion model.

公开(公告)号：US20240144496A1

公开(公告)日：2024-05-02

申请号：US17978463

申请日：2022-11-01

Applicant: Microsoft Technology Licensing, LLC

Inventor： Paul LEE ,  Michael BLEYER ,  Christian Markus MAEKELAE

IPC: G06T7/33 ,  G06T11/00

CPC classification number: G06T7/33 ,  G06T11/00 ,  G06T2207/20221

Abstract: Techniques for performing image alignment between a first image generated by a first camera and a second image generated by a second camera are disclosed. The image alignment is performed using staggered feature extraction in which a set of features are reused to align the second image with the first image. A first set of features are identified from within the first image, and a second set of features, which were previously detected within the second image, are accessed. The second set of features were previously used at least once to perform a previous image alignment operation. A current image alignment operation is performed by using the first set of features and by reusing the second set of features to align the first image with the second image.

公开(公告)号：US20240362891A1

公开(公告)日：2024-10-31

申请号：US18306671

申请日：2023-04-25

Applicant: Microsoft Technology Licensing, LLC

Inventor： Michael BLEYER ,  Pascal PARÉ ,  Paul LEE ,  Aleksander Bogdan BAPST

IPC: G06V10/74 ,  G06V10/25 ,  G06V10/44

CPC classification number: G06V10/761 ,  G06V10/25 ,  G06V10/44

Abstract: A system for selecting motion models for aligning scene content captured by different image sensors, is configurable to (i) access a first image captured by a first image sensor and a second image captured by a second image sensor; (ii) access a set of motion models; (iii) define a reference patch within the second image; (iv) generate a respective match patch for each motion model of the set of motion models; (v) determine a similarity between each respective match patch and the reference patch within the second image; (vi) select a final motion model from the set of motion models based upon the similarity between each respective match patch and the reference patch within the second image; and (vii) utilize the final motion model to generate an output image for display to a user.

公开(公告)号：US20240144526A1

公开(公告)日：2024-05-02

申请号：US17978526

申请日：2022-11-01

Applicant: Microsoft Technology Licensing, LLC

Inventor： Paul LEE ,  Michael BLEYER ,  Christian Markus MAEKELAE

IPC: G06T7/73 ,  G06T7/246 ,  G06T19/00

CPC classification number: G06T7/74 ,  G06T7/251 ,  G06T19/006

Abstract: Techniques for generating an aggregated set of features from multiple images generated by a camera are disclosed. A first image generated by the camera is accessed, where the first image was generated at a first time. A first set of features are identified from within the first image. A second image generated by the camera is accessed, where the second image is generated at a subsequent, second time. A second set of features are identified from within the second image. Movement data is obtained. This movement data details a movement of the camera between the first and second times. The movement data is used to reproject a pose embodied in the first image to correspond to a pose embodied in the second image. The embodiments aggregate the two sets of features to generate the aggregated set of features. The aggregated set of features for the camera are then cached.