Patents by Inventor Philippe Paris
Philippe Paris 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: 20230342592Abstract: A generative neural network control system controls a generative neural network by modifying the intermediate latent space in the generative neural network. The generative neural network includes multiple layers each generating a set of activation values. An initial layer (and optionally additional layers) receives an input latent vector, and a final layer outputs an image generated based on the input latent vector. The data that is input to each layer (other than the initial layer) is referred to as data in an intermediate latent space. The data in the intermediate latent space includes activation values (e.g., generated by the previous layer or modified using various techniques) and optionally a latent vector. The generative neural network control system modifies the intermediate latent space to achieve various different effects when generating a new image.Type: ApplicationFiled: April 17, 2023Publication date: October 26, 2023Applicant: Adobe Inc.Inventors: Sylvain Philippe Paris, Erik Andreas Härkönen, Aaron Phillip Hertzmann
-
Patent number: 11657255Abstract: A generative neural network control system controls a generative neural network by modifying the intermediate latent space in the generative neural network. The generative neural network includes multiple layers each generating a set of activation values. An initial layer (and optionally additional layers) receives an input latent vector, and a final layer outputs an image generated based on the input latent vector. The data that is input to each layer (other than the initial layer) is referred to as data in an intermediate latent space. The data in the intermediate latent space includes activation values (e.g., generated by the previous layer or modified using various techniques) and optionally a latent vector. The generative neural network control system modifies the intermediate latent space to achieve various different effects when generating a new image.Type: GrantFiled: February 21, 2020Date of Patent: May 23, 2023Assignee: Adobe Inc.Inventors: Sylvain Philippe Paris, Erik Andreas Härkönen, Aaron Phillip Hertzmann
-
Patent number: 11615292Abstract: A target image is projected into a latent space of generative model by determining a latent vector by applying a gradient-free technique and a class vector by applying a gradient-based technique. An image is generated from the latent and class vectors, and a loss function is used to determine a loss between the target image and the generated image. This determining of the latent vector and the class vector, generating an image, and using the loss function is repeated until a loss condition is satisfied. In response to the loss condition being satisfied, the latent and class vectors that resulted in the loss condition being satisfied are identified as the final latent and class vectors, respectively. The final latent and class vectors are provided to the generative model and multiple weights of the generative model are adjusted to fine-tune the generative model.Type: GrantFiled: August 31, 2022Date of Patent: March 28, 2023Assignee: Adobe Inc.Inventors: Richard Zhang, Sylvain Philippe Paris, Junyan Zhu, Aaron Phillip Hertzmann, Jacob Minyoung Huh
-
Patent number: 11553777Abstract: The invention relates to a cover intended to close a vial for dispensing a fluid product, the cover including a hollow body and an insert inserted in the hollow body. The insert includes a platform including an upper face delimited by a peripheral edge and featuring a central axis; a skirt extending along the central axis from the platform and featuring an outer surface; an empty volume defined by: a base corresponding to a surface of the upper face included between, on the one hand, the peripheral edge and, on the other, a joint between the platform and the outer surface of the skirt, and a height corresponding to the height of the skirt; The insert further includes the means for filling the empty volume.Type: GrantFiled: October 21, 2019Date of Patent: January 17, 2023Assignee: Albea ServicesInventors: Gael Thorez, Laurent Pesqueux, Philippe Paris
-
Patent number: 11544365Abstract: Systems and methods for authenticating a user for accessing a restricted system are provided. A code presented by the restricted system is acquired. The code visually represents an authentication challenge. The authentication challenge is extracted from the code. Authentication information associated with the user for use in the authentication challenge is received. The user is authenticated for accessing the restricted system based on the authentication information.Type: GrantFiled: March 23, 2020Date of Patent: January 3, 2023Assignee: Bloomberg Finance L.P.Inventor: Philippe Paris Vachon
-
Publication number: 20220414431Abstract: A target image is projected into a latent space of generative model by determining a latent vector by applying a gradient-free technique and a class vector by applying a gradient-based technique. An image is generated from the latent and class vectors, and a loss function is used to determine a loss between the target image and the generated image. This determining of the latent vector and the class vector, generating an image, and using the loss function is repeated until a loss condition is satisfied. In response to the loss condition being satisfied, the latent and class vectors that resulted in the loss condition being satisfied are identified as the final latent and class vectors, respectively. The final latent and class vectors are provided to the generative model and multiple weights of the generative model are adjusted to fine-tune the generative model.Type: ApplicationFiled: August 31, 2022Publication date: December 29, 2022Applicant: Adobe Inc.Inventors: Richard Zhang, Sylvain Philippe Paris, Junyan Zhu, Aaron Phillip Hertzmann, Jacob Minyoung Huh
-
Patent number: 11468294Abstract: A target image is projected into a latent space of generative model by determining a latent vector by applying a gradient-free technique and a class vector by applying a gradient-based technique. An image is generated from the latent and class vectors, and a loss function is used to determine a loss between the target image and the generated image. This determining of the latent vector and the class vector, generating an image, and using the loss function is repeated until a loss condition is satisfied. In response to the loss condition being satisfied, the latent and class vectors that resulted in the loss condition being satisfied are identified as the final latent and class vectors, respectively. The final latent and class vectors are provided to the generative model and multiple weights of the generative model are adjusted to fine-tune the generative model.Type: GrantFiled: February 21, 2020Date of Patent: October 11, 2022Assignee: Adobe Inc.Inventors: Richard Zhang, Sylvain Philippe Paris, Junyan Zhu, Aaron Phillip Hertzmann, Jacob Minyoung Huh
-
Patent number: 11261009Abstract: A removable cap for a dispensing bottle of a fluid product, equipped with a central axis, includes an axis insert being capable of concealing a dispensing system of the bottle. The insert includes a peripheral portion and an upper portion, a first decorative element mounted on the insert and covering the peripheral portion of the insert, a second decorative element mounted on the insert and covering the upper portion of the insert. The second decorative element engages with the first decorative element so as to integrate decorative protrusions within the first decorative element, arranged on the periphery of the cap. The decorative protrusions are arranged on lugs.Type: GrantFiled: September 24, 2019Date of Patent: March 1, 2022Assignee: Albea ServicesInventors: Gael Thorez, Laurent Pesqueux, Philippe Paris
-
Publication number: 20210264235Abstract: A target image is projected into a latent space of generative model by determining a latent vector by applying a gradient-free technique and a class vector by applying a gradient-based technique. An image is generated from the latent and class vectors, and a loss function is used to determine a loss between the target image and the generated image. This determining of the latent vector and the class vector, generating an image, and using the loss function is repeated until a loss condition is satisfied. In response to the loss condition being satisfied, the latent and class vectors that resulted in the loss condition being satisfied are identified as the final latent and class vectors, respectively. The final latent and class vectors are provided to the generative model and multiple weights of the generative model are adjusted to fine-tune the generative model.Type: ApplicationFiled: February 21, 2020Publication date: August 26, 2021Applicant: Adobe Inc.Inventors: Richard Zhang, Sylvain Philippe Paris, Junyan Zhu, Aaron Phillip Hertzmann, Jacob Minyoung Huh
-
Publication number: 20210264234Abstract: A generative neural network control system controls a generative neural network by modifying the intermediate latent space in the generative neural network. The generative neural network includes multiple layers each generating a set of activation values. An initial layer (and optionally additional layers) receives an input latent vector, and a final layer outputs an image generated based on the input latent vector. The data that is input to each layer (other than the initial layer) is referred to as data in an intermediate latent space. The data in the intermediate latent space includes activation values (e.g., generated by the previous layer or modified using various techniques) and optionally a latent vector. The generative neural network control system modifies the intermediate latent space to achieve various different effects when generating a new image.Type: ApplicationFiled: February 21, 2020Publication date: August 26, 2021Applicant: Adobe Inc.Inventors: Sylvain Philippe Paris, Erik Andreas Härkönen, Aaron Phillip Hertzmann
-
Publication number: 20210112944Abstract: The invention relates to a cover intended to close a vial for dispensing a fluid product, the cover including a hollow body and an insert inserted in the hollow body. The insert includes a platform including an upper face delimited by a peripheral edge and featuring a central axis; a skirt extending along the central axis from the platform and featuring an outer surface; an empty volume defined by: a base corresponding to a surface of the upper face included between, on the one hand, the peripheral edge and, on the other, a joint between the platform and the outer surface of the skirt, and a height corresponding to the height of the skirt; The insert further includes the means for filling the empty volume.Type: ApplicationFiled: October 21, 2019Publication date: April 22, 2021Inventors: Gael THOREZ, Laurent PESQUEUX, Philippe PARIS
-
Publication number: 20200302043Abstract: Systems and methods for authenticating a user for accessing a restricted system are provided. A code presented by the restricted system is acquired. The code visually represents an authentication challenge. The authentication challenge is extracted from the code. Authentication information associated with the user for use in the authentication challenge is received. The user is authenticated for accessing the restricted system based on the authentication information.Type: ApplicationFiled: March 23, 2020Publication date: September 24, 2020Applicant: Bloomberg Finance L.P.Inventor: Philippe Paris Vachon
-
Patent number: 10706512Abstract: Methods and systems are provided for adjusting the brightness of images. In some implementations, an exposure bracketed set of input images produced by a camera is received. A brightness adjustment is determined for at least one input image from the set of input images. The determined brightness adjustment is applied to the input image. An output image is produced by exposure fusion from the set of input images, using the input image having the determined brightness adjustment. The output image is transmitted where, the transmitting causes display of the output image on a user device.Type: GrantFiled: March 7, 2017Date of Patent: July 7, 2020Assignee: ADOBE INC.Inventors: Yinglan Ma, Sylvain Philippe Paris, Chih-Yao Hsieh
-
Patent number: 10650490Abstract: Environmental map generation techniques and systems are described. A digital image is scaled to achieve a target aspect ratio using a content aware scaling technique. A canvas is generated that is dimensionally larger than the scaled digital image and the scaled digital image is inserted within the canvas thereby resulting in an unfilled portion of the canvas. An initially filled canvas is then generated by filling the unfilled portion using a content aware fill technique based on the inserted digital image. A plurality of polar coordinate canvases is formed by transforming original coordinates of the canvas into polar coordinates. The unfilled portions of the polar coordinate canvases are filled using a content-aware fill technique that is initialized based on the initially filled canvas. An environmental map of the digital image is generated by combining a plurality of original coordinate canvas portions formed from the polar coordinate canvases.Type: GrantFiled: April 9, 2019Date of Patent: May 12, 2020Assignee: Adobe Inc.Inventors: Xue Bai, Elya Shechtman, Sylvain Philippe Paris
-
Publication number: 20200095025Abstract: A removable cap for a dispensing bottle of a fluid product, equipped with a central axis, includes an axis insert being capable of concealing a dispensing system of the bottle. The insert includes a peripheral portion and an upper portion, a first decorative element mounted on the insert and covering the peripheral portion of the insert, a second decorative element mounted on the insert and covering the upper portion of the insert. The second decorative element engages with the first decorative element so as to integrate decorative protrusions within the first decorative element, arranged on the periphery of the cap. The decorative protrusions are arranged on lugs.Type: ApplicationFiled: September 24, 2019Publication date: March 26, 2020Inventors: Gael Thorez, Laurent Pesqueux, Philippe Paris
-
Publication number: 20190236753Abstract: Environmental map generation techniques and systems are described. A digital image is scaled to achieve a target aspect ratio using a content aware scaling technique. A canvas is generated that is dimensionally larger than the scaled digital image and the scaled digital image is inserted within the canvas thereby resulting in an unfilled portion of the canvas. An initially filled canvas is then generated by filling the unfilled portion using a content aware fill technique based on the inserted digital image. A plurality of polar coordinate canvases is formed by transforming original coordinates of the canvas into polar coordinates. The unfilled portions of the polar coordinate canvases are filled using a content-aware fill technique that is initialized based on the initially filled canvas. An environmental map of the digital image is generated by combining a plurality of original coordinate canvas portions formed from the polar coordinate canvases.Type: ApplicationFiled: April 9, 2019Publication date: August 1, 2019Applicant: Adobe Inc.Inventors: Xue Bai, Elya Shechtman, Sylvain Philippe Paris
-
Patent number: 10282815Abstract: Environmental map generation techniques and systems are described. A digital image is scaled to achieve a target aspect ratio using a content aware scaling technique. A canvas is generated that is dimensionally larger than the scaled digital image and the scaled digital image is inserted within the canvas thereby resulting in an unfilled portion of the canvas. An initially filled canvas is then generated by filling the unfilled portion using a content aware fill technique based on the inserted digital image. A plurality of polar coordinate canvases is formed by transforming original coordinates of the canvas into polar coordinates. The unfilled portions of the polar coordinate canvases are filled using a content-aware fill technique that is initialized based on the initially filled canvas. An environmental map of the digital image is generated by combining a plurality of original coordinate canvas portions formed from the polar coordinate canvases.Type: GrantFiled: December 13, 2016Date of Patent: May 7, 2019Assignee: Adobe Inc.Inventors: Xue Bai, Elya Shechtman, Sylvain Philippe Paris
-
Patent number: D946573Type: GrantFiled: December 4, 2020Date of Patent: March 22, 2022Assignee: BLOOMBERG FINANCE L.P.Inventors: Philippe Paris Vachon, Udai Mathur, Joel Even, Sean Roarty
-
Patent number: D963648Type: GrantFiled: December 18, 2020Date of Patent: September 13, 2022Assignee: Bloomberg Finance L.P.Inventors: Philippe Paris Vachon, Udai Mathur, Joel Even, Sean Roarty
-
Patent number: D983197Type: GrantFiled: December 18, 2020Date of Patent: April 11, 2023Assignee: Bloomberg Finance L.P.Inventors: Philippe Paris Vachon, Udai Mathur, Joel Even, Sean Roarty