Patents by Inventor Vladimir Kim
Vladimir Kim 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).
-
Patent number: 10600239Abstract: Matching an illumination of an embedded virtual object (VO) with current environment illumination conditions provides an enhanced immersive experience to a user. To match the VO and environment illuminations, illumination basis functions are determined based on preprocessing image data, captured as a first combination of intensities of direct illumination sources illuminates the environment. Each basis function corresponds to one of the direct illumination sources. During the capture of runtime image data, a second combination of intensities illuminates the environment. An illumination-weighting vector is determined based on the runtime image data. The determination of the weighting vector accounts for indirect illumination sources, such as surface reflections. The weighting vector encodes a superposition of the basis functions that corresponds to the second combination of intensities. The method illuminates the VO based on the weighting vector.Type: GrantFiled: January 22, 2018Date of Patent: March 24, 2020Assignee: Adobe Inc.Inventors: Jeong Joon Park, Zhili Chen, Xin Sun, Vladimir Kim, Kalyan Krishna Sunkavalli, Duygu Ceylan Aksit
-
Publication number: 20200035010Abstract: This disclosure relates to methods, non-transitory computer readable media, and systems that use style-aware puppets patterned after a source-character-animation sequence to generate a target-character-animation sequence. In particular, the disclosed systems can generate style-aware puppets based on an animation character drawn or otherwise created (e.g., by an artist) for the source-character-animation sequence. The style-aware puppets can include, for instance, a character-deformational model, a skeletal-difference map, and a visual-texture representation of an animation character from a source-character-animation sequence. By using style-aware puppets, the disclosed systems can both preserve and transfer a detailed visual appearance and stylized motion of an animation character from a source-character-animation sequence to a target-character-animation sequence.Type: ApplicationFiled: July 27, 2018Publication date: January 30, 2020Inventors: Vladimir Kim, Wilmot Li, Marek Dvoroznák, Daniel Sýkora
-
Patent number: 10521970Abstract: Certain embodiments involve refining local parameterizations that apply two-dimensional (“2D”) images to three-dimensional (“3D”) models. For instance, a particular parameterization-initialization process is select based on one or more features of a target mesh region. An initial local parameterization for a 2D image is generated from this parameterization-initialization process. A quality metric for the initial local parameterization is computed, and the local parameterization is modified to improve the quality metric. The 3D model is modified by applying image points from the 2D image to the target mesh region in accordance with the modified local parameterization.Type: GrantFiled: February 21, 2018Date of Patent: December 31, 2019Assignee: Adobe Inc.Inventors: Emiliano Gambaretto, Vladimir Kim, Qingnan Zhou, Mehmet Ersin Yumer
-
Publication number: 20190385346Abstract: Techniques are disclosed for the synthesis of a full set of slotted content, based upon only partial observations of the slotted content. With respect to a font, the slots may comprise particular letters or symbols or glyphs in an alphabet. Based upon partial observations of a subset of glyphs from a font, a full set of the glyphs corresponding to the font may be synthesized and may further be ornamented.Type: ApplicationFiled: June 15, 2018Publication date: December 19, 2019Applicant: Adobe Inc.Inventors: Matthew David Fisher, Samaneh Azadi, Vladimir Kim, Elya Shechtman, Zhaowen Wang
-
Patent number: 10467760Abstract: This disclosure involves generating and outputting a segmentation model using 3D models having user-provided labels and scene graphs. For example, a system uses a neural network learned from the user-provided labels to transform feature vectors, which represent component shapes of the 3D models, into transformed feature vectors identifying points in a feature space. The system identifies component-shape groups from clusters of the points in the feature space. The system determines, from the scene graphs, parent-child relationships for the component-shape groups. The system generates a segmentation hierarchy with nodes corresponding to the component-shape groups and links corresponding to the parent-child relationships. The system trains a point classifier to assign feature points, which are sampled from an input 3D shape, to nodes of the segmentation hierarchy, and thereby segment the input 3D shape into component shapes.Type: GrantFiled: February 23, 2017Date of Patent: November 5, 2019Assignee: Adobe Inc.Inventors: Vladimir Kim, Aaron Hertzmann, Mehmet Yumer, Li Yi
-
Publication number: 20190286892Abstract: Certain embodiments detect human-object interactions in image content. For example, human-object interaction metadata is applied to an input image, thereby identifying contact between a part of a depicted human and a part of a depicted object. Applying the human-object interaction metadata involves computing a joint-location heat map by applying a pose estimation subnet to the input image and a contact-point heat map by applying an object contact subnet to the to the input image. The human-object interaction metadata is generated by applying an interaction-detection subnet to the joint-location heat map and the contact-point heat map. The interaction-detection subnet is trained to identify an interaction based on joint-object contact pairs, where a joint-object contact pair includes a relationship between a human joint location and a contact point. An image search system or other computing system is provided with access to the input image having the human-object interaction metadata.Type: ApplicationFiled: March 13, 2018Publication date: September 19, 2019Inventors: Zimo Li, Vladimir Kim, Mehmet Ersin Yumer
-
Publication number: 20190259216Abstract: Certain embodiments involve refining local parameterizations that apply two-dimensional (“2D”) images to three-dimensional (“3D”) models. For instance, a particular parameterization-initialization process is select based on one or more features of a target mesh region. An initial local parameterization for a 2D image is generated from this parameterization-initialization process. A quality metric for the initial local parameterization is computed, and the local parameterization is modified to improve the quality metric. The 3D model is modified by applying image points from the 2D image to the target mesh region in accordance with the modified local parameterization.Type: ApplicationFiled: February 21, 2018Publication date: August 22, 2019Inventors: Emiliano Gambaretto, Vladimir Kim, Qingnan Zhou, Mehmet Ersin Yumer
-
Patent number: 10380317Abstract: Methods and systems for generating digital models from objects. In particular, one or more embodiments determine a plurality of correspondences for first and second components of an object. One or more embodiments estimate a joint connecting the first and second components based on the correspondences. One or more embodiments jointly determine a global transformation and one or more joint parameters that map the plurality of components of the object from the first digital scan to the second digital scan. One or more embodiments also updating the correspondences based on the determined global transformation and parameter(s). One or more embodiments re-estimate the joint based on the updated correspondences. One or more embodiments select a candidate joint with a lowest error estimate from a plurality of candidate joints according to determined global transformations and joint parameter(s) for the candidate joints.Type: GrantFiled: March 7, 2016Date of Patent: August 13, 2019Assignee: ADOBE INC.Inventors: Duygu Ceylan, Byungmoon Kim, Aron Monszpart, Vladimir Kim, Niloy Mitra
-
Publication number: 20190228567Abstract: Matching an illumination of an embedded virtual object (VO) with current environment illumination conditions provides an enhanced immersive experience to a user. To match the VO and environment illuminations, illumination basis functions are determined based on preprocessing image data, captured as a first combination of intensities of direct illumination sources illuminates the environment. Each basis function corresponds to one of the direct illumination sources. During the capture of runtime image data, a second combination of intensities illuminates the environment. An illumination-weighting vector is determined based on the runtime image data. The determination of the weighting vector accounts for indirect illumination sources, such as surface reflections. The weighting vector encodes a superposition of the basis functions that corresponds to the second combination of intensities. The method illuminates the VO based on the weighting vector.Type: ApplicationFiled: January 22, 2018Publication date: July 25, 2019Inventors: Jeong Joon Park, Zhili Chen, Xin Sun, Vladimir Kim, Kalyan Krishna Sunkavalli, Duygu Ceylan Aksit
-
Patent number: 10204423Abstract: Disclosed are techniques for more accurately estimating the pose of a camera used to capture a three-dimensional scene. Accuracy is enhanced by leveraging three-dimensional object priors extracted from a large-scale three-dimensional shape database. This allows existing feature matching techniques to be augmented by generic three-dimensional object priors, thereby providing robust information about object orientations across multiple images or frames. More specifically, the three-dimensional object priors provide a unit that is easier and more reliably tracked between images than a single feature point. By adding object pose estimates across images, drift is reduced and the resulting visual odometry techniques are more robust and accurate. This eliminates the need for three-dimensional object templates that are specifically generated for the imaged object, training data obtained for a specific environment, and other tedious preprocessing steps.Type: GrantFiled: February 13, 2017Date of Patent: February 12, 2019Assignee: Adobe Inc.Inventors: Vladimir Kim, Oliver Wang, Minhyuk Sung, Mehmet Ersin Yumer
-
Publication number: 20180300882Abstract: The present disclosure includes methods and systems for identifying and manipulating a segment of a three-dimensional digital model based on soft classification of the three-dimensional digital model. In particular, one or more embodiments of the disclosed systems and methods identify a soft classification of a digital model and utilize the soft classification to tune segmentation algorithms. For example, the disclosed systems and methods can utilize a soft classification to select a segmentation algorithm from a plurality of segmentation algorithms, to combine segmentation parameters from a plurality of segmentation algorithms, and/or to identify input parameters for a segmentation algorithm. The disclosed systems and methods can utilize the tuned segmentation algorithms to accurately and efficiently identify a segment of a three-dimensional digital model.Type: ApplicationFiled: April 14, 2017Publication date: October 18, 2018Inventors: Vladimir Kim, Aaron Hertzmann, Mehmet Yumer
-
Publication number: 20180240243Abstract: This disclosure involves generating and outputting a segmentation model using 3D models having user-provided labels and scene graphs. For example, a system uses a neural network learned from the user-provided labels to transform feature vectors, which represent component shapes of the 3D models, into transformed feature vectors identifying points in a feature space. The system identifies component-shape groups from clusters of the points in the feature space. The system determines, from the scene graphs, parent-child relationships for the component-shape groups. The system generates a segmentation hierarchy with nodes corresponding to the component-shape groups and links corresponding to the parent-child relationships. The system trains a point classifier to assign feature points, which are sampled from an input 3D shape, to nodes of the segmentation hierarchy, and thereby segment the input 3D shape into component shapes.Type: ApplicationFiled: February 23, 2017Publication date: August 23, 2018Inventors: Vladimir Kim, Aaron Hertzmann, Mehmet Yumer, Li Yi
-
Publication number: 20180232906Abstract: Disclosed are techniques for more accurately estimating the pose of a camera used to capture a three-dimensional scene. Accuracy is enhanced by leveraging three-dimensional object priors extracted from a large-scale three-dimensional shape database. This allows existing feature matching techniques to be augmented by generic three-dimensional object priors, thereby providing robust information about object orientations across multiple images or frames. More specifically, the three-dimensional object priors provide a unit that is easier and more reliably tracked between images than a single feature point. By adding object pose estimates across images, drift is reduced and the resulting visual odometry techniques are more robust and accurate. This eliminates the need for three-dimensional object templates that are specifically generated for the imaged object, training data obtained for a specific environment, and other tedious preprocessing steps.Type: ApplicationFiled: February 13, 2017Publication date: August 16, 2018Applicant: Adobe Systems IncorporatedInventors: Vladimir Kim, Oliver Wang, Minhyuk Sung, Mehmet Ersin Yumer
-
Publication number: 20170255712Abstract: Methods and systems for generating digital models from objects. In particular, one or more embodiments determine a plurality of correspondences for first and second components of an object. One or more embodiments estimate a joint connecting the first and second components based on the correspondences. One or more embodiments jointly determine a global transformation and one or more joint parameters that map the plurality of components of the object from the first digital scan to the second digital scan. One or more embodiments also updating the correspondences based on the determined global transformation and parameter(s). One or more embodiments re-estimate the joint based on the updated correspondences. One or more embodiments select a candidate joint with a lowest error estimate from a plurality of candidate joints according to determined global transformations and joint parameter(s) for the candidate joints.Type: ApplicationFiled: March 7, 2016Publication date: September 7, 2017Inventors: Duygu Ceylan, Byungmoon Kim, Aron Monszpart, Vladimir Kim, Niloy Mitra
-
Patent number: 5892329Abstract: A plasma accelerator with closed electron drift comprising a dielectric discharge chamber (6) with internal and external annular walls (13) forming an annular accelerating channel, and a magnetic system with sources (3) of a magnetic field, a magnetic path (2), external (4) and internal (5) magnetic poles forming an operating gap in the region of the discharge chamber exit edges. An anode unit (7) with a gas distributor is located in the accelerating channel interior, and the distance from the anode-gas distributor (7) to the accelerating channel exit plane exceeds said channel width. A cathode-compensator (1) is located beyond the exit plane of the discharge chamber (6). Exit parts of the discharge chamber walls (13) facing the accelerating channel are made of conducting material. At least one dividing annular groove (12) is made on each chamber wall between its conducting and main parts.Type: GrantFiled: May 23, 1997Date of Patent: April 6, 1999Assignee: International Space Technology, Inc.Inventors: Boris A. Arkhipov, Vitaly V. Egorov, Vladimir Kim, Vyacheslav I. Kozlov, Nicolay A. Maslennikov, Sergei A. Khartov
-
Patent number: 5218271Abstract: A plasma accelerator with closed electron drift includes a magnetic system (4), a cathode (10), and a discharge chamber with an annular acceleration passage (3) accommodating a hollow anode (7) communicating therewith by way of at least one outlet passage (8). The outlet passage (8) is curved, and a straight line drawn from any interior of anode (7) to any point in the acceleration passage (3) intersects walls of anode (7).Type: GrantFiled: June 21, 1991Date of Patent: June 8, 1993Assignee: Research Institute of Applied Mechanics and Electrodynamics of Moscow Aviation InstituteInventors: Vitaly V. Egorov, Vladimir M. Gavrushin, Vladimir Kim, Vyacheslav I. Kozlov, Leonid A. Latyshev, Sergey A. Khartov
-
Patent number: 4425180Abstract: The present drum can find application mainly for assembling large-size tire casings.The drum comprises sectors with shoulders provided with a drive for their radial movement. The drive incorporates slide-blocks arranged concentrically with each other on a shaft axially movable therealong. The slide-blocks are articulated, through levers, with the sectors. The midpoint of one of the levers of each slide-block is articulated with the shaft through the link which is half as long as the lever.The shoulders are provided with a mechanism for their relative movement with respect to the sector. The mechanism is made as a cam associated with the lever of radial movement drive of the sector. The cam is adapted to engage one of the toothed segments articulated to the sector. The toothed segments are kinematically associated with each other and are in mesh with the respective toothed racks connected to the shoulders, so that the toothed segment engages the cam through the agency of a pin provided on the cam.Type: GrantFiled: July 8, 1981Date of Patent: January 10, 1984Assignee: Vsesojuzny Nauchno-Issledovatelsky I Konstruktorsky Institut Po Oborudovaniju Dlya Shinnoi PromyshlennostiInventors: Jury I. Samokhvalov, Vladimir A. Kim, Engels K. Golovkin
-
Patent number: 4126507Abstract: The tire-building drum comprises alternate drum sectors with fixedly and movably mounted shoulders and mechanisms for moving said drum sectors. Each of these mechanisms consists of two parts having annular slides, which are connected to a screw drive, and levers, which are articulated to the drum sectors and the slides and which have toothed sectors arranged in constant mesh with each other for the purpose of inter-connecting the parts in each of the mechanisms for moving the drum sectors. The slides are mounted coaxially on the drum hub and are adapted to move together and separately in mutually opposite directions. This enables the drum sectors to move only radially and decreases the axial dimensions of the drum.Type: GrantFiled: April 6, 1977Date of Patent: November 21, 1978Inventors: Vladimir A. Kim, Jury I. Samokhvalov, Boris M. Petrov, Engels K. Golovkin, Galina N. Artamonova