Patents by Inventor Seyed Morteza Safdarnejad
Seyed Morteza Safdarnejad 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: 20230281763Abstract: Methods, systems, and non-transitory computer readable storage media are disclosed for utilizing a plurality of neural networks in a multi-branch pipeline to generate image masks for digital images. Specifically, the disclosed system can classify a digital image as a portrait or a non-portrait image. Based on classifying a portrait image, the disclosed system can utilize separate neural networks to generate a first mask portion for a portion of the digital image including a defined boundary region and a second mask portion for a portion of the digital image including a blended boundary region. The disclosed system can generate the mask portion for the blended boundary region by utilizing a trimap generation neural network to automatically generate a trimap segmentation including the blended boundary region. The disclosed system can then merge the first mask portion and the second mask portion to generate an image mask for the digital image.Type: ApplicationFiled: May 15, 2023Publication date: September 7, 2023Inventors: He Zhang, Seyed Morteza Safdarnejad, Yilin Wang, Zijun Wei, Jianming Zhang, Salil Tambe, Brian Price
-
Patent number: 11651477Abstract: Methods, systems, and non-transitory computer readable storage media are disclosed for utilizing a plurality of neural networks in a multi-branch pipeline to generate image masks for digital images. Specifically, the disclosed system can classify a digital image as a portrait or a non-portrait image. Based on classifying a portrait image, the disclosed system can utilize separate neural networks to generate a first mask portion for a portion of the digital image including a defined boundary region and a second mask portion for a portion of the digital image including a blended boundary region. The disclosed system can generate the mask portion for the blended boundary region by utilizing a trimap generation neural network to automatically generate a trimap segmentation including the blended boundary region. The disclosed system can then merge the first mask portion and the second mask portion to generate an image mask for the digital image.Type: GrantFiled: August 7, 2020Date of Patent: May 16, 2023Assignee: Adobe Inc.Inventors: He Zhang, Seyed Morteza Safdarnejad, Yilin Wang, Zijun Wei, Jianming Zhang, Salil Tambe, Brian Price
-
Publication number: 20230129341Abstract: The present disclosure relates to systems, methods, and non-transitory computer-readable media that generate preliminary object masks for objects in an image, surface the preliminary object masks as object mask previews, and on-demand converts preliminary object masks into refined object masks. Indeed, in one or more implementations, an object mask preview and on-demand generation system automatically detects objects in an image. For the detected objects, the object mask preview and on-demand generation system generates preliminary object masks for the detected objects of a first lower resolution. The object mask preview and on-demand generation system surfaces a given preliminary object mask in response to detecting a first input. The object mask preview and on-demand generation system also generates a refined object mask of a second higher resolution in response to detecting a second input.Type: ApplicationFiled: January 25, 2022Publication date: April 27, 2023Inventors: Betty Leong, Hyunghwan Byun, Alan L Erickson, Chih-Yao Hsieh, Sarah Kong, Seyed Morteza Safdarnejad, Salil Tambe, Yilin Wang, Zijun Wei, Zhengyun Zhang
-
Patent number: 11551338Abstract: The present disclosure is directed toward intelligently mixing and matching faces and/or people to generate an enhanced image that reduces or minimize artifacts and other defects. For example, the disclosed systems can selectively apply different alignment models to determine a relative alignment between a references image and a target image having an improved instance of the person. Upon aligning the digital images, the disclosed systems can intelligently identify a replacement region based on a boundary that includes the target instance and the reference instance of the person without intersecting other objects or people in the image. Using the size and shape of the replacement region around the target instance and the reference instance, the systems replace the instance of the person in the reference image with the target instance. The alignment of the images and the intelligent selection of the replacement region minimizes inconsistencies and/or artifacts in the final image.Type: GrantFiled: November 23, 2020Date of Patent: January 10, 2023Assignee: Adobe Inc.Inventors: Seyed Morteza Safdarnejad, Chih-Yao Hsieh
-
Patent number: 11393100Abstract: Methods, systems, and non-transitory computer readable storage media are disclosed for utilizing a plurality of neural networks in a multi-branch pipeline to generate image masks for digital images. Specifically, the disclosed system can classify a digital image as a portrait or a non-portrait image. Based on classifying a portrait image, the disclosed system can utilize separate neural networks to generate a first mask portion for a portion of the digital image including a defined boundary region and a second mask portion for a portion of the digital image including a blended boundary region. The disclosed system can generate the mask portion for the blended boundary region by utilizing a trimap generation neural network to automatically generate a trimap segmentation including the blended boundary region. The disclosed system can then merge the first mask portion and the second mask portion to generate an image mask for the digital image.Type: GrantFiled: August 7, 2020Date of Patent: July 19, 2022Assignee: Adobe Inc.Inventors: He Zhang, Seyed Morteza Safdarnejad, Yilin Wang, Zijun Wei, Jianming Zhang, Salil Tambe, Brian Price
-
Publication number: 20220044365Abstract: Methods, systems, and non-transitory computer readable storage media are disclosed for utilizing a plurality of neural networks in a multi-branch pipeline to generate image masks for digital images. Specifically, the disclosed system can classify a digital image as a portrait or a non-portrait image. Based on classifying a portrait image, the disclosed system can utilize separate neural networks to generate a first mask portion for a portion of the digital image including a defined boundary region and a second mask portion for a portion of the digital image including a blended boundary region. The disclosed system can generate the mask portion for the blended boundary region by utilizing a trimap generation neural network to automatically generate a trimap segmentation including the blended boundary region. The disclosed system can then merge the first mask portion and the second mask portion to generate an image mask for the digital image.Type: ApplicationFiled: August 7, 2020Publication date: February 10, 2022Inventors: He Zhang, Seyed Morteza Safdarnejad, Yilin Wang, Zijun Wei, Jianming Zhang, Salil Tambe, Brian Price
-
Publication number: 20220044366Abstract: Methods, systems, and non-transitory computer readable storage media are disclosed for utilizing a plurality of neural networks in a multi-branch pipeline to generate image masks for digital images. Specifically, the disclosed system can classify a digital image as a portrait or a non-portrait image. Based on classifying a portrait image, the disclosed system can utilize separate neural networks to generate a first mask portion for a portion of the digital image including a defined boundary region and a second mask portion for a portion of the digital image including a blended boundary region. The disclosed system can generate the mask portion for the blended boundary region by utilizing a trimap generation neural network to automatically generate a trimap segmentation including the blended boundary region. The disclosed system can then merge the first mask portion and the second mask portion to generate an image mask for the digital image.Type: ApplicationFiled: August 7, 2020Publication date: February 10, 2022Inventors: He Zhang, Seyed Morteza Safdarnejad, Yilin Wang, Zijun Wei, Jianming Zhang, Salil Tambe, Brian Price
-
Patent number: 11216961Abstract: This disclosure relates to methods, non-transitory computer readable media, and systems that analyze feature points of digital images to selectively apply a pixel-adjusted-gyroscope-alignment model and a feature-based-alignment model to align the digital images. For instance, the disclosed systems can select an appropriate alignment model based on feature-point-deficiency metrics specific to an input image and reference-input image. Moreover, in certain implementations, the pixel-adjusted-gyroscope-alignment model utilizes parameters from pixel-based alignment and gyroscope-based alignment to align such digital images. Together with the feature-based-alignment model, the disclosed methods, non-transitory computer readable media, and systems can use a selective image-alignment algorithm that improves computational efficiency, accuracy, and flexibility in generating enhanced digital images from a set of input images.Type: GrantFiled: August 27, 2020Date of Patent: January 4, 2022Assignee: ADOBE INC.Inventors: Seyed Morteza Safdarnejad, Chih-Yao Hsieh
-
Patent number: 11196939Abstract: This disclosure relates to methods, non-transitory computer readable media, and systems that generate a virtual long exposure image from a sequence of short exposure images portraying a moving object. In various embodiments, the image transformation system aligns two digital images in the sequence of short exposure images. The image transformation system can determine a motion vector path for the moving object between the first digital image and the second digital image. The image transformation system can also blend pixels along the motion vector path to generate a blended image representative of the motion of the moving object between the first digital image and the second digital image. The image transformation system can generate additional blended images based on consecutive pairs of images in the sequence of digital images and generates a virtual long exposure image by combining the first blended image with the additional blended images.Type: GrantFiled: May 18, 2020Date of Patent: December 7, 2021Assignee: ADOBE INC.Inventors: Chih-Yao Hsieh, Sylvain Paris, Seyed Morteza Safdarnejad, Gregg Wilensky
-
Publication number: 20210073961Abstract: The present disclosure is directed toward intelligently mixing and matching faces and/or people to generate an enhanced image that reduces or minimize artifacts and other defects. For example, the disclosed systems can selectively apply different alignment models to determine a relative alignment between a references image and a target image having an improved instance of the person. Upon aligning the digital images, the disclosed systems can intelligently identify a replacement region based on a boundary that includes the target instance and the reference instance of the person without intersecting other objects or people in the image. Using the size and shape of the replacement region around the target instance and the reference instance, the systems replace the instance of the person in the reference image with the target instance. The alignment of the images and the intelligent selection of the replacement region minimizes inconsistencies and/or artifacts in the final image.Type: ApplicationFiled: November 23, 2020Publication date: March 11, 2021Inventors: Seyed Morteza Safdarnejad, Chih-Yao Hsieh
-
Patent number: 10896493Abstract: The present disclosure is directed toward intelligently mixing and matching faces and/or people to generate an enhanced image that reduces or minimize artifacts and other defects. For example, the disclosed systems can selectively apply different alignment models to determine a relative alignment between a references image and a target image having an improved instance of the person. Upon aligning the digital images, the disclosed systems can intelligently identify a replacement region based on a boundary that includes the target instance and the reference instance of the person without intersecting other objects or people in the image. Using the size and shape of the replacement region around the target instance and the reference instance, the systems replace the instance of the person in the reference image with the target instance. The alignment of the images and the intelligent selection of the replacement region minimizes inconsistencies and/or artifacts in the final image.Type: GrantFiled: November 13, 2018Date of Patent: January 19, 2021Assignee: ADOBE INC.Inventors: Seyed Morteza Safdarnejad, Chih-Yao Hsieh
-
Publication number: 20200394808Abstract: This disclosure relates to methods, non-transitory computer readable media, and systems that analyze feature points of digital images to selectively apply a pixel-adjusted-gyroscope-alignment model and a feature-based-alignment model to align the digital images. For instance, the disclosed systems can select an appropriate alignment model based on feature-point-deficiency metrics specific to an input image and reference-input image. Moreover, in certain implementations, the pixel-adjusted-gyroscope-alignment model utilizes parameters from pixel-based alignment and gyroscope-based alignment to align such digital images. Together with the feature-based-alignment model, the disclosed methods, non-transitory computer readable media, and systems can use a selective image-alignment algorithm that improves computational efficiency, accuracy, and flexibility in generating enhanced digital images from a set of input images.Type: ApplicationFiled: August 27, 2020Publication date: December 17, 2020Inventors: Seyed Morteza Safdarnejad, Chih-Yao Hsieh
-
Patent number: 10796421Abstract: Embodiments of the present invention are directed to facilitating images with selective application of the long-exposure effect. In accordance with some embodiments of the present invention, virtual long-exposure image comprising a plurality of aligned frames is provided and a selection of a region of pixels in the virtual long-exposure image is received. The virtual long-exposure image is combined with one of the frames forming the virtual long-exposure image to create a selective virtual long-exposure image. The selective virtual long-exposure image comprises a visible portion of the original virtual long-exposure image and a visible portion of the individual frame that corresponds to the selected region of pixels. Additional frames may be combined with the virtual long-exposure image to create a plurality of selective virtual long-exposure image options, and the user may select one for continued use or for saving.Type: GrantFiled: February 13, 2018Date of Patent: October 6, 2020Inventors: Seyed Morteza Safdarnejad, Sarah Aye Kong, Gregg Darryl Wilensky, Chih-Yao Hsieh
-
Patent number: 10783649Abstract: This disclosure relates to methods, non-transitory computer readable media, and systems that analyze feature points of digital images to selectively apply a pixel-adjusted-gyroscope-alignment model and a feature-based-alignment model to align the digital images. For instance, the disclosed systems can select an appropriate alignment model based on feature-point-deficiency metrics specific to an input image and reference-input image. Moreover, in certain implementations, the pixel-adjusted-gyroscope-alignment model utilizes parameters from pixel-based alignment and gyroscope-based alignment to align such digital images. Together with the feature-based-alignment model, the disclosed methods, non-transitory computer readable media, and systems can use a selective image-alignment algorithm that improves computational efficiency, accuracy, and flexibility in generating enhanced digital images from a set of input images.Type: GrantFiled: September 17, 2018Date of Patent: September 22, 2020Assignee: ADOBE INC.Inventors: Seyed Morteza Safdarnejad, Chih-Yao Hsieh
-
Publication number: 20200280670Abstract: This disclosure relates to methods, non-transitory computer readable media, and systems that generate a virtual long exposure image from a sequence of short exposure images portraying a moving object. In various embodiments, the image transformation system aligns two digital images in the sequence of short exposure images. The image transformation system can determine a motion vector path for the moving object between the first digital image and the second digital image. The image transformation system can also blend pixels along the motion vector path to generate a blended image representative of the motion of the moving object between the first digital image and the second digital image. The image transformation system can generate additional blended images based on consecutive pairs of images in the sequence of digital images and generates a virtual long exposure image by combining the first blended image with the additional blended images.Type: ApplicationFiled: May 18, 2020Publication date: September 3, 2020Inventors: Chih-Yao Hsieh, Sylvain Paris, Seyed Morteza Safdarnejad, Gregg Wilensky
-
Patent number: 10701279Abstract: This disclosure relates to methods, non-transitory computer readable media, and systems that generate a virtual long exposure image from a sequence of short exposure images portraying a moving object. In various embodiments, the image transformation system aligns two digital images in the sequence of short exposure images. The image transformation system can determine a motion vector path for the moving object between the first digital image and the second digital image. The image transformation system can also blend pixels along the motion vector path to generate a blended image representative of the motion of the moving object between the first digital image and the second digital image. The image transformation system can generate additional blended images based on consecutive pairs of images in the sequence of digital images and generates a virtual long exposure image by combining the first blended image with the additional blended images.Type: GrantFiled: October 2, 2018Date of Patent: June 30, 2020Assignee: ADOBE INC.Inventors: Chih-Yao Hsieh, Sylvain Paris, Seyed Morteza Safdarnejad, Gregg Wilensky
-
Publication number: 20200151860Abstract: The present disclosure is directed toward intelligently mixing and matching faces and/or people to generate an enhanced image that reduces or minimize artifacts and other defects. For example, the disclosed systems can selectively apply different alignment models to determine a relative alignment between a references image and a target image having an improved instance of the person. Upon aligning the digital images, the disclosed systems can intelligently identify a replacement region based on a boundary that includes the target instance and the reference instance of the person without intersecting other objects or people in the image. Using the size and shape of the replacement region around the target instance and the reference instance, the systems replace the instance of the person in the reference image with the target instance. The alignment of the images and the intelligent selection of the replacement region minimizes inconsistencies and/or artifacts in the final image.Type: ApplicationFiled: November 13, 2018Publication date: May 14, 2020Inventors: Seyed Morteza Safdarnejad, Chih-Yao Hsieh
-
Publication number: 20200106945Abstract: This disclosure relates to methods, non-transitory computer readable media, and systems that generate a virtual long exposure image from a sequence of short exposure images portraying a moving object. In various embodiments, the image transformation system aligns two digital images in the sequence of short exposure images. The image transformation system can determine a motion vector path for the moving object between the first digital image and the second digital image. The image transformation system can also blend pixels along the motion vector path to generate a blended image representative of the motion of the moving object between the first digital image and the second digital image. The image transformation system can generate additional blended images based on consecutive pairs of images in the sequence of digital images and generates a virtual long exposure image by combining the first blended image with the additional blended images.Type: ApplicationFiled: October 2, 2018Publication date: April 2, 2020Inventors: Chih-Yao Hsieh, Sylvain Paris, Seyed Morteza Safdarnejad, Gregg Wilensky
-
Publication number: 20200090351Abstract: This disclosure relates to methods, non-transitory computer readable media, and systems that analyze feature points of digital images to selectively apply a pixel-adjusted-gyroscope-alignment model and a feature-based-alignment model to align the digital images. For instance, the disclosed systems can select an appropriate alignment model based on feature-point-deficiency metrics specific to an input image and reference-input image. Moreover, in certain implementations, the pixel-adjusted-gyroscope-alignment model utilizes parameters from pixel-based alignment and gyroscope-based alignment to align such digital images. Together with the feature-based-alignment model, the disclosed methods, non-transitory computer readable media, and systems can use a selective image-alignment algorithm that improves computational efficiency, accuracy, and flexibility in generating enhanced digital images from a set of input images.Type: ApplicationFiled: September 17, 2018Publication date: March 19, 2020Inventors: Seyed Morteza Safdarnejad, Chih-Yao Hsieh
-
Patent number: 10573052Abstract: Embodiments of the present invention are directed to facilitate creating cinemagraphs from virtual long-exposure images. In accordance with some embodiments of the present invention, virtual long-exposure image comprising a plurality of aligned frames is provided and a selection of a region of pixels in the virtual long-exposure image is received. Based on the selected region of pixels, a set of frames for animation is identified from the plurality of frames. The set of frames may be identified by automatically detecting a sequence of frames or by receiving a user selection of frames. The virtual LE image is combined with the set of frames to create a cinemagraph having a visible non-animated portion formed by the virtual LE image and a visible animated portion formed by the set of frames.Type: GrantFiled: February 13, 2018Date of Patent: February 25, 2020Assignee: ADOBE INC.Inventors: Seyed Morteza Safdarnejad, Sarah Aye Kong, Chih-Yao Hsieh