Patents by Inventor Chenge Li
Chenge Li 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: 11748850Abstract: Embodiments relate to a super-resolution engine that converts a lower resolution input image into a higher resolution output image. The super-resolution engine includes a directional scaler, an enhancement processor, a feature detection processor, a blending logic circuit, and a neural network. The directional scaler generates directionally scaled image data by upscaling the input image. The enhancement processor generates enhanced image data by applying an example-based enhancement, a peaking filter, or some other type of non-neural network image processing scheme to the directionally scaled image data. The feature detection processor determines features indicating properties of portions of the directionally scaled image data. The neural network generates residual values defining differences between a target result of the super-resolution enhancement and the directionally scaled image data. The blending logic circuit blends the enhanced image data with the residual values according to the features.Type: GrantFiled: April 15, 2022Date of Patent: September 5, 2023Assignee: Apple Inc.Inventors: Jim Chen Chou, Chenge Li, Yun Gong
-
Publication number: 20220270208Abstract: Embodiments relate to a super-resolution engine that converts a lower resolution input image into a higher resolution output image. The super-resolution engine includes a directional scaler, an enhancement processor, a feature detection processor, a blending logic circuit, and a neural network. The directional scaler generates directionally scaled image data by upscaling the input image. The enhancement processor generates enhanced image data by applying an example-based enhancement, a peaking filter, or some other type of non-neural network image processing scheme to the directionally scaled image data. The feature detection processor determines features indicating properties of portions of the directionally scaled image data. The neural network generates residual values defining differences between a target result of the super-resolution enhancement and the directionally scaled image data. The blending logic circuit blends the enhanced image data with the residual values according to the features.Type: ApplicationFiled: April 15, 2022Publication date: August 25, 2022Inventors: Jim Chen Chou, Chenge Li, Yun Gong
-
Patent number: 11308582Abstract: Embodiments relate to a super-resolution engine that converts a lower resolution input image into a higher resolution output image. The super-resolution engine includes a directional scaler, an enhancement processor, a feature detection processor, a blending logic circuit, and a neural network. The directional scaler generates directionally scaled image data by upscaling the input image. The enhancement processor generates enhanced image data by applying an example-based enhancement, a peaking filter, or some other type of non-neural network image processing scheme to the directionally scaled image data. The feature detection processor determines features indicating properties of portions of the directionally scaled image data. The neural network generates residual values defining differences between a target result of the super-resolution enhancement and the directionally scaled image data. The blending logic circuit blends the enhanced image data with the residual values according to the features.Type: GrantFiled: April 9, 2020Date of Patent: April 19, 2022Assignee: Apple Inc.Inventors: Jim Chen Chou, Chenge Li, Yun Gong
-
Patent number: 11162951Abstract: Fluorescent labeling of proteins. In particular, membrane-impermeant fluorogenic chromophores being capable of binding reversibly a functional derivative of a Photoactive Yellow Protein (PYP), or a functional fragment thereof, for fluorescently labeling biological molecules of interest, preferably proteins of interest. Especially, 4-hydroxybenzylidene-rhodanine (HBR) analogs of formula (II) as membrane-impermeant fluorogenic chromophores.Type: GrantFiled: May 18, 2018Date of Patent: November 2, 2021Assignees: PARIS SCIENCES ET LETTRES, CENTRE NATIONAL DE LA RECHERCHE SCIENTIFIQUE, INSTITUT CURIE, SORBONNE UNIVERSITEInventors: Arnaud Gautier, Ludovic Jullien, Chenge Li, Franck Perez
-
Publication number: 20200294196Abstract: Embodiments relate to a super-resolution engine that converts a lower resolution input image into a higher resolution output image. The super-resolution engine includes a directional scaler, an enhancement processor, a feature detection processor, a blending logic circuit, and a neural network. The directional scaler generates directionally scaled image data by upscaling the input image. The enhancement processor generates enhanced image data by applying an example-based enhancement, a peaking filter, or some other type of non-neural network image processing scheme to the directionally scaled image data. The feature detection processor determines features indicating properties of portions of the directionally scaled image data. The neural network generates residual values defining differences between a target result of the super-resolution enhancement and the directionally scaled image data. The blending logic circuit blends the enhanced image data with the residual values according to the features.Type: ApplicationFiled: April 9, 2020Publication date: September 17, 2020Inventors: Jim Chen Chou, Chenge Li, Yun Gong
-
Publication number: 20200124611Abstract: Fluorescent labeling of proteins. In particular, membrane-impermeant fluorogenic chromophores being capable of binding reversibly a functional derivative of a Photoactive Yellow Protein (PYP), or a functional fragment thereof, for fluorescently labeling biological molecules of interest, preferably proteins of interest. Especially, 4-hydroxybenzylidene-rhodanine (HBR) analogs of formula (II) as membrane-impermeant fluorogenic chromophores.Type: ApplicationFiled: May 18, 2018Publication date: April 23, 2020Applicants: PARIS SCIENCES ET LETTRES - QUARTIER LATIN, CENTRE NATIONAL DE LA RECHERCHE SCIENTIFIQUE, INSTITUT CURIE, SORBONNE UNIVERSITEInventors: Arnaud GAUTIER, Ludovic JULLIEN, Chenge LI, Franck PEREZ
-
Patent number: 10621697Abstract: Embodiments relate to a super-resolution engine that converts a lower resolution input image into a higher resolution output image. The super-resolution engine includes a directional scaler, an enhancement processor, a feature detection processor, a blending logic circuit, and a neural network. The directional scaler generates directionally scaled image data by upscaling the input image. The enhancement processor generates enhanced image data by applying an example-based enhancement, a peaking filter, or some other type of non-neural network image processing scheme to the directionally scaled image data. The feature detection processor determines features indicating properties of portions of the directionally scaled image data. The neural network generates residual values defining differences between a target result of the super-resolution enhancement and the directionally scaled image data. The blending logic circuit blends the enhanced image data with the residual values according to the features.Type: GrantFiled: August 6, 2018Date of Patent: April 14, 2020Assignee: Apple Inc.Inventors: Jim Chen Chou, Chenge Li, Yun Gong
-
Publication number: 20200043135Abstract: Embodiments relate to a super-resolution engine that converts a lower resolution input image into a higher resolution output image. The super-resolution engine includes a directional scaler, an enhancement processor, a feature detection processor, a blending logic circuit, and a neural network. The directional scaler generates directionally scaled image data by upscaling the input image. The enhancement processor generates enhanced image data by applying an example-based enhancement, a peaking filter, or some other type of non-neural network image processing scheme to the directionally scaled image data. The feature detection processor determines features indicating properties of portions of the directionally scaled image data. The neural network generates residual values defining differences between a target result of the super-resolution enhancement and the directionally scaled image data. The blending logic circuit blends the enhanced image data with the residual values according to the features.Type: ApplicationFiled: August 6, 2018Publication date: February 6, 2020Inventors: Jim Chen Chou, Chenge Li, Yun Gong