Patents by Inventor Xiaolin Wei
Xiaolin Wei has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).
-
Publication number: 20170148155Abstract: A method of determining camera poses includes capturing a plurality of image frames using a camera, computing relative poses between each set of image frame pairs to provide a relative pose set and an uncategorized relative pose set, and detecting and removing miscategorized relative poses to provide a remaining relative pose set. The method also includes determining global poses using the remaining relative pose set and computing extended relative poses for at least a portion of the miscategorized relative poses and at least a portion of the uncategorized relative pose set to provide an extended relative pose set and an extended uncategorized relative pose set. The method further includes detecting and removing extended miscategorized relative poses to provide a remaining extended relative pose set and determining updated global poses for the plurality of image frames using the remaining relative pose set and the remaining extended relative pose set.Type: ApplicationFiled: November 18, 2016Publication date: May 25, 2017Applicant: Magic Leap, Inc.Inventor: Xiaolin Wei
-
Publication number: 20170091996Abstract: A method for forming a reconstructed 3D mesh includes receiving a set of captured depth maps associated with a scene, performing an initial camera pose alignment associated with the set of captured depth maps, and overlaying the set of captured depth maps in a reference frame. The method also includes detecting one or more shapes in the overlaid set of captured depth maps and updating the initial camera pose alignment to provide a shape-aware camera pose alignment. The method further includes performing shape-aware volumetric fusion and forming the reconstructed 3D mesh associated with the scene.Type: ApplicationFiled: September 23, 2016Publication date: March 30, 2017Applicant: Magic Leap, Inc.Inventors: Xiaolin Wei, Yifu Zhang
-
Patent number: 9437034Abstract: Systems and methods for generating textures to be rendered in conjunction with a polygon mesh are provided. More particularly, a polygon mesh modeling a geographic area can be accessed. A plurality of source images depicting the geographic area can then be identified. The plurality of source images can be aligned to reduce projection misalignments between source images when the source images are projected to the polygon mesh. A texture can then be determined based at least in part on a weighted average of pixels in the plurality of source images corresponding to a point on the surface of the polygon mesh. Determining a texture can include removing at least one outlier pixel associated with a moving object from the weighted average.Type: GrantFiled: December 15, 2014Date of Patent: September 6, 2016Assignee: Google Inc.Inventors: Xiaolin Wei, Tilman Reinhardt
-
Patent number: 9373190Abstract: A novel stereo reconstruction pipeline that features depth map alignment and outlier identification is provided. One example method includes obtaining a plurality of images depicting a scene. The method includes determining a pose for each of the plurality of images. The method includes determining a depth map for each of the plurality of images such that a plurality of depth maps are determined. Each of the plurality of depth maps describes a plurality of points in three-dimensional space that correspond to objects in the scene. The method includes aligning the plurality of depth maps by transforming one or more of the plurality of depth maps so as to improve an alignment between the plurality of depth maps. The method includes identifying one or more outlying points. The method includes generating a three-dimensional model of the scene based at least in part on the plurality of depth maps.Type: GrantFiled: July 9, 2014Date of Patent: June 21, 2016Assignee: Google Inc.Inventors: Xiaolin Wei, Aleksey Golovinskiy
-
Patent number: 9373192Abstract: Systems and methods for simplifying a three-dimensional mesh providing a three-dimensional model, such as a three-dimensional model of a cityscape, are provided. In particular, mesh simplification techniques can preserve important structural shapes in the original three-dimensional mesh. Important features in a representation of a city scene or other scene can be represented by structural edges (e.g. building outlines, bridges, curved structures such as curved highway overpasses, etc.). These structural edges can be detected and a representation of the structural edges can be constructed in the mesh. The mesh can then be simplified using the structural edges as high-level simplification criterion such that the structural edges are preserved during simplification.Type: GrantFiled: June 12, 2013Date of Patent: June 21, 2016Assignee: Google Inc.Inventor: Xiaolin Wei
-
Publication number: 20160012633Abstract: A novel stereo reconstruction pipeline that features depth map alignment and outlier identification is provided. One example method includes obtaining a plurality of images depicting a scene. The method includes determining a pose for each of the plurality of images. The method includes determining a depth map for each of the plurality of images such that a plurality of depth maps are determined Each of the plurality of depth maps describes a plurality of points in three-dimensional space that correspond to objects in the scene. The method includes aligning the plurality of depth maps by transforming one or more of the plurality of depth maps so as to improve an alignment between the plurality of depth maps. The method includes identifying one or more outlying points. The method includes generating a three-dimensional model of the scene based at least in part on the plurality of depth maps.Type: ApplicationFiled: July 9, 2014Publication date: January 14, 2016Inventors: Xiaolin Wei, Aleksey Golovinskiy
-
Patent number: 9196050Abstract: Systems and methods for image-based bridge identification and boundary detection are provided. One example method includes determining, by one or more computing devices, a wide bridge mask and a narrow bridge mask based at least in part on a road mask and a water mask. The method includes selecting, by the one or more computing devices, a portion of an image depicting a bridge based at least in part on the wide bridge mask and the narrow bridge mask. The method includes identifying, by the one or more computing devices, a plurality of line features included in the portion of the image depicting the bridge. The method includes determining, by the one or more computing devices, a bridge boundary in the portion of the image based at least in part on the plurality of line features. One example system includes a bridge image extraction module and a bridge boundary determination module.Type: GrantFiled: April 9, 2014Date of Patent: November 24, 2015Assignee: Google Inc.Inventors: Xiaolin Wei, Hui Lou
-
Publication number: 20150294477Abstract: Systems and methods for image-based bridge identification and boundary detection are provided. One example method includes determining, by one or more computing devices, a wide bridge mask and a narrow bridge mask based at least in part on a road mask and a water mask. The method includes selecting, by the one or more computing devices, a portion of an image depicting a bridge based at least in part on the wide bridge mask and the narrow bridge mask. The method includes identifying, by the one or more computing devices, a plurality of line features included in the portion of the image depicting the bridge. The method includes determining, by the one or more computing devices, a bridge boundary in the portion of the image based at least in part on the plurality of line features. One example system includes a bridge image extraction module and a bridge boundary determination module.Type: ApplicationFiled: April 9, 2014Publication date: October 15, 2015Applicant: Google Inc.Inventors: Xiaolin Wei, Hui Lou
-
Patent number: 9001129Abstract: A processing apparatus for creating an avatar is provided. The processing apparatus calculates skeleton sizes of joints of the avatar and local coordinates corresponding to sensors attached to a target user, by minimizing a sum of a difference function and a skeleton prior function, the difference function representing a difference between a forward kinematics function regarding the joints with respect to reference poses of the target user and positions of the sensors, and the skeleton prior function based on statistics of skeleton sizes with respect to reference poses of a plurality of users.Type: GrantFiled: October 19, 2011Date of Patent: April 7, 2015Assignees: Samsung Electronics Co., Ltd., Texas A&M University SystemInventors: Taehyun Rhee, Inwoo Ha, Dokyoon Kim, Xiaolin Wei, Jinxiang Chai, Huajun Liu
-
Publication number: 20140368498Abstract: Systems and methods for simplifying a three-dimensional mesh providing a three-dimensional model, such as a three-dimensional model of a cityscape, are provided. In particular, mesh simplification techniques can preserve important structural shapes in the original three-dimensional mesh. Important features in a representation of a city scene or other scene can be represented by structural edges (e.g. building outlines, bridges, curved structures such as curved highway overpasses, etc.). These structural edges can be detected and a representation of the structural edges can be constructed in the mesh. The mesh can then be simplified using the structural edges as high-level simplification criterion such that the structural edges are preserved during simplification.Type: ApplicationFiled: June 12, 2013Publication date: December 18, 2014Inventor: Xiaolin Wei
-
Patent number: 8655810Abstract: A data processing apparatus is used for motion synthesis. A preprocessing unit of the data processing apparatus calculates a mixture of factor analysis (MFA) parameter by applying an energy minimized optimization algorithm to motion capture data acquired in advance and stored in a motion database (DB). When a motion probability distribution model is generated as described above, a calculating unit of the data processing apparatus synthesizes a motion corresponding to input motion sensing data by applying the input motion sensing data to the motion probability distribution model.Type: GrantFiled: October 21, 2011Date of Patent: February 18, 2014Assignees: Samsung Electronics Co., Ltd., The Texas A&M University SystemInventors: Jinxiang Chai, Inwoo Ha, Taehyun Rhee, Dokyoon Kim, Huajun Liu, Xiaolin Wei
-
Publication number: 20120136817Abstract: A data processing apparatus is used for motion synthesis. A preprocessing unit of the data processing apparatus calculates a mixture of factor analysis (MFA) parameter by applying an energy minimized optimization algorithm to motion capture data acquired in advance and stored in a motion database (DB). When a motion probability distribution model is generated as described above, a calculating unit of the data processing apparatus synthesizes a motion corresponding to input motion sensing data by applying the input motion sensing data to the motion probability distribution model.Type: ApplicationFiled: October 21, 2011Publication date: May 31, 2012Applicants: The Texas A&M University System, Samsung Electronics Co., Ltd.Inventors: Jinxiang Chai, Inwoo Ha, Taehyun Rhee, Dokyoon Kim, Huajun Liu, Xiaolin Wei
-
Publication number: 20120127164Abstract: A processing apparatus for creating an avatar is provided. The processing apparatus calculates skeleton sizes of joints of the avatar and local coordinates corresponding to sensors attached to a target user, by minimizing a sum of a difference function and a skeleton prior function, the difference function representing a difference between a forward kinematics function regarding the joints with respect to reference poses of the target user and positions of the sensors, and the skeleton prior function based on statistics of skeleton sizes with respect to reference poses of a plurality of users.Type: ApplicationFiled: October 19, 2011Publication date: May 24, 2012Applicants: Texas A&M University System, SAMSUNG ELECTRONICS CO., LTD.Inventors: Taehyun RHEE, Inwoo Ha, Dokyoon Kim, Xiaolin Wei, Jinxiang Chai, Huajun Liu
-
Patent number: 8142647Abstract: A process for adsorbing aromatic sulfur compounds, where an adsorbent is contacted with a C6-C20 aromatic and/or aliphatic stream which comprises a solution of (i) at least one benzothiophene compound, (ii) a solvent which comprises at least one C6-C16 aliphatic compound, and (iii) optionally at least one C6-C12 aromatic compound. In this process, the adsorbent is regenerated using an organic regenerant such as, but not limited to, toluene. Also disclosed is another process for adsorbing aromatic sulfur compounds. In this process, an adsorbent is contacted with a mixture comprising a model diesel feed comprising at least one benzothiophene compound. In this process, the adsorbent is regenerated using an organic regenerant such as, but not limited to, toluene.Type: GrantFiled: December 16, 2008Date of Patent: March 27, 2012Assignee: Chevron U.S.A. Inc.Inventors: Xiaolin Wei, Scott M. Husson, Marcus V. Dutra e Mello, Daniel Chinn, Zunqing He
-
Patent number: 8138369Abstract: A process for producing an adsorbent where a metal oxide is reacted with an alkoxy silane to produce an epoxy-functionalized metal oxide. This product is reacted with an amino-substituted propionic acid and a nitro-substituted fluorenone, and this product is grafted to the epoxy-functionalized metal oxide. This grafted product is the adsorbent, which may be contacted with a hydrocarbon mixture having at least one sulfur containing compound in order to remove this sulfur containing compound. Also disclosed is a process for adding polymerization groups to an adsorbent.Type: GrantFiled: June 6, 2008Date of Patent: March 20, 2012Assignee: Chevron U.S.A. Inc.Inventors: Xiaolin Wei, Scott Michael Husson, Marcus V. Dutra e Mello, Daniel Chinn
-
Publication number: 20100147748Abstract: A process for adsorbing aromatic sulfur compounds, where an adsorbent is contacted with a C6-C20 aromatic and/or aliphatic stream which comprises a solution of (i) at least one benzothiophene compound, (ii) a solvent which comprises at least one C6-C16 aliphatic compound, and (iii) optionally at least one C6-C12 aromatic compound. In this process, the adsorbent is regenerated using an organic regenerant such as, but not limited to, toluene. Also disclosed is another process for adsorbing aromatic sulfur compounds. In this process, an adsorbent is contacted with a mixture comprising a model diesel feed comprising at least one benzothiophene compound. In this process, the adsorbent is regenerated using an organic regenerant such as, but not limited to, toluene.Type: ApplicationFiled: December 16, 2008Publication date: June 17, 2010Inventors: Xiaolin Wei, Scott M. Husson, Marcus V. Dutra e Mello, Daniel Chinn, Zunqing He
-
Publication number: 20090076221Abstract: A process for producing an adsorbent where a metal oxide is reacted with an alkoxy silane to produce an epoxy-functionalized metal oxide. This product is reacted with an amino-substituted propionic acid and a nitro-substituted fluorenone, and this product is grafted to the epoxy-functionalized metal oxide. This grafted product is the adsorbent, which may be contacted with a hydrocarbon mixture having at least one sulfur containing compound in order to remove this sulfur containing compound. Also disclosed is a process for adding polymerization groups to an adsorbent.Type: ApplicationFiled: June 6, 2008Publication date: March 19, 2009Inventors: Xiaolin Wei, Scott Michael Husson, Marcus V. Dutra e Mello, Daniel Chinn