Patents by Inventor Stephen S. Lin
Stephen S. Lin 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: 10846887Abstract: Techniques and constructs can determine an albedo map and a shading map from a digital image. The albedo and shading maps can be determined based at least in part on a color-difference threshold. A color shading map can be determined based at least in part on the albedo map, and lighting coefficients determined based on the color shading map. The digital image can be adjusted based at least in part on the lighting coefficients. In some examples, respective shading maps can be produced for individual color channels of the digital image. The color shading map can be produced based at least in part on the shading maps. In some examples, a plurality of regions of the digital image can be determined, as can proximity relationships between individual regions. The albedo shading maps can be determined based at least in part on the proximity relationships.Type: GrantFiled: June 24, 2016Date of Patent: November 24, 2020Assignee: Microsoft Technology Licensing, LLCInventors: Yue Dong, Xin Tong, Lin Liang, Jian Shi, Stephen S. Lin, Simon Stachniak
-
Patent number: 10713816Abstract: Disclosed in some examples, are methods, systems, and machine readable mediums that correct image color casts by utilizing a fully convolutional network (FCN), where the patches in an input image may differ in influence over the color constancy estimation. This influence is formulated as a confidence weight that reflects the value of a patch for inferring the illumination color. The confidence weights are integrated into a novel pooling layer where they are applied to local patch estimates in determining a global color constancy result.Type: GrantFiled: July 14, 2017Date of Patent: July 14, 2020Assignee: Microsoft Technology Licensing, LLCInventors: Yuanming Hu, Baoyuan Wang, Stephen S. Lin
-
Publication number: 20190019311Abstract: Disclosed in some examples, are methods, systems, and machine readable mediums that correct image color casts by utilizing a fully convolutional network (FCN), where the patches in an input image may differ in influence over the color constancy estimation. This influence is formulated as a confidence weight that reflects the value of a patch for inferring the illumination color. The confidence weights are integrated into a novel pooling layer where they are applied to local patch estimates in determining a global color constancy result.Type: ApplicationFiled: July 14, 2017Publication date: January 17, 2019Inventors: Yuanming Hu, Baoyuan Wang, Stephen S. Lin
-
Publication number: 20180189978Abstract: Techniques and constructs can determine an albedo map and a shading map from a digital image. The albedo and shading maps can be determined based at least in part on a color-difference threshold. A color shading map can be determined based at least in part on the albedo map, and lighting coefficients determined based on the color shading map. The digital image can be adjusted based at least in part on the lighting coefficients. In some examples, respective shading maps can be produced for individual color channels of the digital image. The color shading map can be produced based at least in part on the shading maps. In some examples, a plurality of regions of the digital image can be determined, as can proximity relationships between individual regions. The albedo shading maps can be determined based at least in part on the proximity relationships.Type: ApplicationFiled: June 24, 2016Publication date: July 5, 2018Applicant: MICROSOFT TECHNOLOGY LICENSING, LLCInventors: Yue DONG, Xin TONG, Lin LIANG, Jian SHI, Stephen S. LIN, Simon STACHNIAK
-
Patent number: 9992457Abstract: The use of a hybrid camera tool may capture high resolution multispectral images without sacrificing resolution in exchange for spectral accuracy. The capture of a high resolution multispectral image may include forming a high spatial resolution image based on a portion of incoming light and generating a high spectral resolution image that includes multispectral samples based on another portion of the incoming light. The high resolution multispectral image is then synthesized by consolidating the high spatial resolution image with the high spectral resolution image.Type: GrantFiled: December 14, 2016Date of Patent: June 5, 2018Assignee: Microsoft Technology Licensing, LLCInventors: Stephen S. Lin, Xin Tong, Xun Cao
-
Patent number: 9684996Abstract: Some implementations disclosed herein provide techniques and arrangements to render global light transport in real-time or near real-time. For example, in a pre-computation stage, a first computing device may render points of surfaces (e.g., using multiple light bounces and the like). Attributes for each of the points may be determined. A plurality of machine learning algorithms may be trained using particular attributes from the attributes. For example, a first machine learning algorithm may be trained using a first portion of the attributes and a second machine learning algorithm may be trained using a second portion of the attributes. The trained machine learning algorithms may be used by a second computing device to render components (e.g., diffuse and specular components) of indirect shading in real-time.Type: GrantFiled: March 19, 2015Date of Patent: June 20, 2017Assignee: Microsoft Technology Licensing, LLCInventors: Jiaping Wang, Peiran Ren, Baining Guo, Minmin Gong, Xin Tong, Stephen S. Lin
-
Patent number: 9635274Abstract: The use of a hybrid camera tool may capture high resolution multispectral images without sacrificing resolution in exchange for spectral accuracy. The capture of a high resolution multispectral image may include forming a high spatial resolution image based on a portion of incoming light and generating a high spectral resolution image that includes multispectral samples based on another portion of the incoming light. The high resolution multispectral image is then synthesized by consolidating the high spatial resolution image with the high spectral resolution image.Type: GrantFiled: June 15, 2011Date of Patent: April 25, 2017Assignee: Microsoft Technology Licensing, LLCInventors: Stephen S. Lin, Xin Tong, Xun Cao
-
Publication number: 20170094233Abstract: The use of a hybrid camera tool may capture high resolution multispectral images without sacrificing resolution in exchange for spectral accuracy. The capture of a high resolution multispectral image may include forming a high spatial resolution image based on a portion of incoming light and generating a high spectral resolution image that includes multispectral samples based on another portion of the incoming light. The high resolution multispectral image is then synthesized by consolidating the high spatial resolution image with the high spectral resolution image.Type: ApplicationFiled: December 14, 2016Publication date: March 30, 2017Inventors: Stephen S. Lin, Xin Tong, Xun Cao
-
Publication number: 20150193967Abstract: Some implementations disclosed herein provide techniques and arrangements to render global light transport in real-time or near real-time. For example, in a pre-computation stage, a first computing device may render points of surfaces (e.g., using multiple light bounces and the like). Attributes for each of the points may be determined. A plurality of machine learning algorithms may be trained using particular attributes from the attributes. For example, a first machine learning algorithm may be trained using a first portion of the attributes and a second machine learning algorithm may be trained using a second portion of the attributes. The trained machine learning algorithms may be used by a second computing device to render components (e.g., diffuse and specular components) of indirect shading in real-time.Type: ApplicationFiled: March 19, 2015Publication date: July 9, 2015Inventors: Jiaping Wang, Peiran Ren, Baining Guo, Minmin Gong, Xin Tong, Stephen S. Lin
-
Patent number: 9013496Abstract: Some implementations disclosed herein provide techniques and arrangements to render global light transport in real-time or near real-time. For example, in a pre-computation stage, a first computing device may render points of surfaces (e.g., using multiple light bounces and the like). Attributes for each of the points may be determined. A plurality of machine learning algorithms may be trained using particular attributes from the attributes. For example, a first machine learning algorithm may be trained using a first portion of the attributes and a second machine learning algorithm may be trained using a second portion of the attributes. The trained machine learning algorithms may be used by a second computing device to render components (e.g., diffuse and specular components) of indirect shading in real-time.Type: GrantFiled: June 19, 2012Date of Patent: April 21, 2015Assignee: Microsoft Technology Licensing, LLCInventors: Jiaping Wang, Peiran Ren, Minmin Gong, Xin Tong, Stephen S. Lin, Baining Guo
-
Patent number: 8922556Abstract: A light gathering process may reduce the computational resources and storage required to render a scene with a participating homogeneous media. According to some implementations, Efficiency may be obtained by evaluating the final radiance along a viewing ray directly from the lighting rays passing near to it, and by rapidly identifying such lighting rays in the scene. To facilitate a search for nearby lighting rays, the lighting rays and viewing rays may be represented as a 6D point and a plane according to the corresponding Plucker coordinates and coefficients, respectively.Type: GrantFiled: April 18, 2011Date of Patent: December 30, 2014Assignee: Microsoft CorporationInventors: Sun Xin, Stephen S. Lin, Baining Guo
-
Patent number: 8730240Abstract: An exemplary method includes providing image data for an illuminated physical sample of a heterogeneous translucent material, determining one or more material properties of the material based in part on a diffusion equation where one of the material properties is a diffusion coefficient for diffusion of radiation in the material and where the determining includes a regularization term for the diffusion coefficient, mapping the one or more material properties to a virtual object volume, assigning virtual illumination conditions to the virtual object volume, and rendering the virtual object volume using the virtual illumination conditions as a boundary condition for a system of diffusion equations of the virtual object volume. Other methods, devices and systems are also disclosed.Type: GrantFiled: August 13, 2012Date of Patent: May 20, 2014Assignee: Microsoft CorporationInventors: Jiaping Wang, Xin Tong, Stephen S. Lin, Baining Guo, Heung-Yeung Shum, Zhouchen Lin
-
Publication number: 20140085502Abstract: The use of a hybrid camera tool may capture high resolution multispectral images without sacrificing resolution in exchange for spectral accuracy. The capture of a high resolution multispectral image may include forming a high spatial resolution image based on a portion of incoming light and generating a high spectral resolution image that includes multispectral samples based on another portion of the incoming light. The high resolution multispectral image is then synthesized by consolidating the high spatial resolution image with the high spectral resolution image.Type: ApplicationFiled: June 15, 2011Publication date: March 27, 2014Applicant: MICROSOFT CORPORATIONInventors: Stephen S. Lin, Xin Tong, Xun Cao
-
Publication number: 20130335434Abstract: Some implementations disclosed herein provide techniques and arrangements to render global light transport in real-time or near real-time. For example, in a pre-computation stage, a first computing device may render points of surfaces (e.g., using multiple light bounces and the like). Attributes for each of the points may be determined. A plurality of machine learning algorithms may be trained using particular attributes from the attributes. For example, a first machine learning algorithm may be trained using a first portion of the attributes and a second machine learning algorithm may be trained using a second portion of the attributes. The trained machine learning algorithms may be used by a second computing device to render components (e.g., diffuse and specular components) of indirect shading in real-time.Type: ApplicationFiled: June 19, 2012Publication date: December 19, 2013Applicant: MICROSOFT CORPORATIONInventors: Jiaping Wang, Peiran Ren, Minmin Gong, Xin Tong, Stephen S. Lin, Baining Guo
-
Publication number: 20120306878Abstract: An exemplary method includes providing image data for an illuminated physical sample of a heterogeneous translucent material, determining one or more material properties of the material based in part on a diffusion equation where one of the material properties is a diffusion coefficient for diffusion of radiation in the material and where the determining includes a regularization term for the diffusion coefficient, mapping the one or more material properties to a virtual object volume, assigning virtual illumination conditions to the virtual object volume, and rendering the virtual object volume using the virtual illumination conditions as a boundary condition for a system of diffusion equations of the virtual object volume. Other methods, devices and systems are also disclosed.Type: ApplicationFiled: August 13, 2012Publication date: December 6, 2012Applicant: MICROSOFT CORPORATIONInventors: Jiaping Wang, Xin Tong, Stephen S. Lin, Baining Guo, Heung-Yeung Shum, Zhouchen Lin
-
Publication number: 20120262456Abstract: A light gathering process may reduce the computational resources and storage required to render a scene with a participating homogeneous media. According to some implementations, Efficiency may be obtained by evaluating the final radiance along a viewing ray directly from the lighting rays passing near to it, and by rapidly identifying such lighting rays in the scene. To facilitate a search for nearby lighting rays, the lighting rays and viewing rays may be represented as a 6D point and a plane according to the corresponding Plucker coordinates and coefficients, respectively.Type: ApplicationFiled: April 18, 2011Publication date: October 18, 2012Applicant: Microsoft CorporationInventors: Sun Xin, Stephen S. Lin, Baining Guo
-
Patent number: 8243071Abstract: An exemplary method includes providing image data for an illuminated physical sample of a heterogeneous translucent material, determining one or more material properties of the material based in part on a diffusion equation where one of the material properties is a diffusion coefficient for diffusion of radiation in the material and where the determining includes a regularization term for the diffusion coefficient, mapping the one or more material properties to a virtual object volume, assigning virtual illumination conditions to the virtual object volume, and rendering the virtual object volume using the virtual illumination conditions as a boundary condition for a system of diffusion equations of the virtual object volume. Other methods, devices and systems are also disclosed.Type: GrantFiled: February 29, 2008Date of Patent: August 14, 2012Assignee: Microsoft CorporationInventors: Jiaping Wang, Xin Tong, Stephen S. Lin, Baining Guo, Heung-Yeung Shum, Zhouchen Lin
-
Patent number: 7986830Abstract: Radiometric calibration of an image capture device (e.g., a digital camera) using a single image is described. The single image may be a color image or a grayscale image. The calibration identifies and analyzes edge pixels of the image that correspond to an edge between two colors or grayscale levels of a scene. Intensity distributions of intensities measured from the single image are then analyzed. An inverse response function for the image capture device is determined based on the intensity distributions. For a color image, the radiometric calibration involves calculating an inverse response function that maps measured blended colors of edge pixels and the associated measured component colors into linear distributions. For a grayscale image, the radiometric calibration involves deriving an inverse response function that maps non-uniform histograms of measured intensities into uniform distributions of calibrated intensities.Type: GrantFiled: December 3, 2008Date of Patent: July 26, 2011Assignee: Microsoft CorporationInventors: Stephen S. Lin, Baining Guo, Heung-Yeung Shum, Jinwei Gu
-
Patent number: 7884820Abstract: Interactive relighting with dynamic reflectance involves relighting a graphical scene with dynamic changes to the reflectance(s) in the graphical scene. A graphical scene may include source radiance, regions having reflectances, a surface spot, incident radiation from the source radiance at the surface sport, an incident direction, a viewing direction, exit radiance, and so forth. In an example embodiment, a graphical scene is relighted based on at least one adjusted reflectance of the graphical scene using an incident radiance at a surface spot that is separated into respective incident radiance components corresponding to different respective numbers of interreflections in the graphical scene. In another example embodiment, a graphical scene is relighted based on at least one adjusted reflectance of the graphical scene using a tensor representation for a reflectance of a surface spot with the tensor representation being segmented into three adjustable factors for lighting, viewing, and reflectance.Type: GrantFiled: June 15, 2007Date of Patent: February 8, 2011Assignee: Micorsoft CorporationInventors: Kun Zhou, Yanyun Chen, Stephen S. Lin, Baining Guo
-
Patent number: 7586494Abstract: The present surface detail rendering technique provides an efficient technique for applying a mesostructure to a macrostructure for an object that minimizes the amount of memory required for pre-computed data. A leap texture is pre-computed for a mesostructure by classifying each voxel in the mesostructure geometry and assigning a value in the leap texture based upon the classification. The value in the leap texture represents a distance to jump along a ray cast in any view direction when a model is decorated with the mesostructure geometry.Type: GrantFiled: March 17, 2006Date of Patent: September 8, 2009Assignee: Microsoft CorporationInventors: Xi Wang, Xin Tong, Stephen S. Lin, Baining Guo