Patents Assigned to ETH ZURICH (EIDGENOESSISCHE TECHNISCHE HOCHSCHULE ZURICH)
-
Patent number: 10475165Abstract: Supervised machine learning using convolutional neural network (CNN) is applied to denoising images rendered by MC path tracing. The input image data may include pixel color and its variance, as well as a set of auxiliary buffers that encode scene information (e.g., surface normal, albedo, depth, and their corresponding variances). In some embodiments, a CNN directly predicts the final denoised pixel value as a highly non-linear combination of the input features. In some other embodiments, a kernel-prediction neural network uses a CNN to estimate the local weighting kernels, which are used to compute each denoised pixel from its neighbors. In some embodiments, the input image can be decomposed into diffuse and specular components. The diffuse and specular components are then independently preprocessed, filtered, and postprocessed, before recombining them to obtain a final denoised image.Type: GrantFiled: November 15, 2017Date of Patent: November 12, 2019Assignees: Disney Enterprises, Inc., ETH Zürich (Eidgenössische Technische Hochschule ZürichInventors: Thijs Vogels, Jan Novák, Fabrice Rousselle, Brian McWilliams
-
Publication number: 20190333190Abstract: Systems and methods for distortion removal at multiple quality levels are disclosed. In one embodiment, a method may include receiving training content. The training content may include original content, reconstructed content, and training distortion quality levels corresponding to the reconstructed content. The reconstructed content may be derived from distorted original content. The method may also include training distortion quality levels corresponding to the reconstructed content. The method may further include receiving an initial distortion removal model. The method may include generating a conditioned distortion removal model by training the initial distortion removal model using the training content. The method may further include storing the conditioned distortion removal model.Type: ApplicationFiled: October 22, 2018Publication date: October 31, 2019Applicants: Disney Enterprises, Inc., ETH Zürich (Eidgenössische Technische Hochschule Zürich)Inventors: Christopher Schroers, Mauro Bamert, Erika Doggett, Jared McPhillen, Scott Labrozzi, Romann Weber
-
Patent number: 10399327Abstract: Embodiments herein describe deformable controllers that rely on piezoelectric material embedded in the controllers to detect when the input device is being manipulated into a particular deformation or gesture. The computing system may perform different actions depending on which deformation is detected. The embodiments herein describe design techniques for optimizing the placement of the piezoelectric material in the controller to improve the accuracy of a mapping function that maps sensor responses of the material to different controller deformations. In one embodiment, the user specifies the different deformations of the controller she wishes to be recognized by the computing system (e.g., raising a leg, twisting a torso, squeezing a hand, etc.). The design optimizer uses the locations of the desired deformations to move the location of the piezoelectric material such that the sensor response of the material can be uniquely mapped to these locations.Type: GrantFiled: April 22, 2016Date of Patent: September 3, 2019Assignees: Disney Enterprises, Inc., ETH Zurich (Eidgenoessische Technische Hochschule ZurichInventors: Moritz Niklaus Bächer, Benjamin Hepp, Fabrizio Pece, Paul Gregory Kry, Bernd Bickel, Bernhard Steffen Thomaszewski, Otmar Hilliges
-
Patent number: 10375200Abstract: A recommender engine is configured to access memory and surface transmedia content items; and/or linked transmedia content subsets; and/or one or more identifications of identified users; and/or content items of the plurality of transmedia content items associated with at least one identified user. The surfaced items are presented for selection by the given user via the transmedia content linking engine as one or more user-selected transmedia content items.Type: GrantFiled: September 26, 2016Date of Patent: August 6, 2019Assignees: DISNEY ENTERPRISES, INC., ETH ZÜRICH (EIDGENÖSSISCHE TECHNISCHE HOCHSCHULE ZÜRICH)Inventors: Barbara Solenthaler, Tanja Kaeser, Severin Klingler, Adriano Galati, Markus Gross
-
Patent number: 10319080Abstract: Enhanced removing of noise and outliers from one or more point sets generated by image-based 3D reconstruction techniques is provided. In accordance with the disclosure, input images and corresponding depth maps can be used to remove pixels that are geometrically and/or photometrically inconsistent with the colored surface implied by the input images. This allows standard surface reconstruction methods (such as Poisson surface reconstruction) to perform less smoothing and thus achieve higher quality surfaces with more features. In some implementations, the enhanced point-cloud noise removal in accordance with the disclosure can include computing per-view depth maps, and detecting and removing noisy points and outliers from each per-view point cloud by checking if points are consistent with the surface implied by the other input views.Type: GrantFiled: July 6, 2018Date of Patent: June 11, 2019Assignees: DISNEY ENTERPRISES, INC., ETH ZÜRICH (EIDGENÖSSISCHE TECHNISCHE HOCHSCHULE ZÜRICH)Inventors: Changil Kim, Olga Sorkine-Hornung, Christopher Schroers, Henning Zimmer, Katja Wolff, Mario Botsch, Alexander Sorkine-Hornung
-
Patent number: 10297065Abstract: Methods, systems, and computer-readable memory are provided for determining time-varying anatomical and physiological tissue characteristics of an animation rig. For example, shape and material properties are defined for a plurality of sample configurations of the animation rig. The shape and material properties are associated with the plurality of sample configurations. An animation of the animation rig is obtained, and one or more configurations of the animation rig are determined for one or more frames of the animation. The determined one or more configurations include shape and material properties, and are determined using one or more sample configurations of the animation rig. A simulation of the animation rig is performed using the determined one or more configurations. Performing the simulation includes computing physical effects for addition to the animation of the animation rig.Type: GrantFiled: November 9, 2016Date of Patent: May 21, 2019Assignees: DISNEY ENTERPRISES, INC., ETH ZÜRICH (EIDGENÖSSISCHE TECHNISCHE HOCHSCHULE ZÜRICH)Inventors: Yeara Kozlov, Bernhard Thomaszewski, Thabo Beeler, Derek Bradley, Moritz Bächer, Markus Gross
-
Publication number: 20190098370Abstract: The invention relates to systems and methods for manipulating non-linearly connected transmedia content, in particular for creating, processing and/or managing non-linearly connected transmedia content and for tracking content creation and attributing transmedia content to one or more creators. Specifically, the invention involves creating a transmedia content data item by a first user and storing the transmedia content data item in a data store, along with a record indicating an association between the first user and the transmedia content data item; creating an ordered group of transmedia content data items by a second user, the ordered group comprising a pointer to the transmedia content data item of the first user; and storing the ordered group and a record associating both the first user and the second user with the ordered group in the data store.Type: ApplicationFiled: September 26, 2017Publication date: March 28, 2019Applicants: DISNEY ENTERPRISES, INC., ETH Zürich (Eidgenössische Technische Hochschule Zürich)Inventors: Rebekkah Laeuchli, Sasha Schriber, Stephan Veen, Markus Gross, Isabel Simo, Max Grosse
-
Publication number: 20190095446Abstract: The invention relates to systems and methods for navigating, outputting and displaying non-linearly connected groups of transmedia content. Specifically, the invention involves retrieving, from a database, an ordered group of transmedia content data objects comprising a plurality of transmedia content data objects and linking data, whereby each element of the linking data defines a directional link from one of the transmedia content data objects to another of the transmedia content data objects; generating a two-dimensional graph structure representing the ordered group of transmedia content data objects whereby each graph node corresponds to a transmedia content data object and each graph edge corresponds to an element of the linking data; and outputting the graph structure on a display screen.Type: ApplicationFiled: September 26, 2017Publication date: March 28, 2019Applicants: DISNEY ENTERPRISES, INC., ETH Zürich (Eidgenössische Technische Hochschule Zürich)Inventors: Rebekkah Laeuchli, Isabel Simo, Max Grosse, Markus Gross, Sasha Schriber, Maria Cabral, Merada Richter
-
Publication number: 20190095435Abstract: The present invention relates to systems and methods for manipulating non-linearly connected transmedia content, in particular for creating, processing and managing non-linearly connected transmedia content. The disclosure includes content creation modes and version control systems for non-linearly connected transmedia content data, in which individual transmedia content data items are connected to either other via directional linking data.Type: ApplicationFiled: September 26, 2017Publication date: March 28, 2019Applicants: DISNEY ENTERPRISES, INC., ETH Zürich (Eidgenössische Technische Hochschule Zürich)Inventors: Rebekkah Laeuchli, Isabel Simo, Max Grosse, Sasha Schriber, Markus Gross, Maria Cabral
-
Publication number: 20190096094Abstract: The present disclosure relates to an apparatus, system and method for processing transmedia content data. More specifically, the disclosure provides for identifying and inserting one item of media content within another item of media content, e.g. inserting a video within a video, such that the first item of media content appears as part of the second item. The invention involves analysing a first visual media item to identify one or more spatial locations to insert the second visual media item within the image data of the first visual media item, detecting characteristics of the one or more identified spatial locations, transforming the second visual media item according to the detected characteristics and combining the first visual media item and second visual media item by inserting the transformed second visual media item into the first visual media item at the one or more identified spatial locations.Type: ApplicationFiled: September 26, 2017Publication date: March 28, 2019Applicants: DISNEY ENTERPRISES, INC., ETH Zürich (Eidgenössische Technische Hochschule Zürich)Inventors: Alex Sorkine-Hornung, Simone Meier, Jean-Charles Bazin, Sasha Schriber, Markus Gross, Oliver Wang
-
Patent number: 10217265Abstract: Systems and techniques for generating a parametric eye model of one or more eyes are provided. The systems and techniques may include obtaining eye data from an eye model database. The eye data includes eyeball data and iris data corresponding to a plurality of eyes. The systems and techniques may further include generating an eyeball model using the eyeball data. Generating the eyeball model includes establishing correspondences among the plurality of eyes. The systems and techniques may further include generating an iris model using the iris data. Generating the iris model includes sampling one or more patches of one or more of the plurality of eyes using an iris control map and merging the one or more patches into a synthesized texture. The systems and techniques may further include generating the parametric eye model that includes the eyeball model and the iris model.Type: GrantFiled: July 7, 2016Date of Patent: February 26, 2019Assignees: DISNEY ENTERPRISES, INC., ETH ZÜRICH (EIDGENÖSSISCHE TECHNISCHE HOCHSCHULE ZÜRICH)Inventors: Pascal Bérard, Thabo Beeler, Derek Bradley, Markus Gross
-
Patent number: 10169910Abstract: The disclosure provides an approach for rendering heterogeneous polydisperse granular media. In one aspect, a rendering application renders such granular media using a combination of explicit path tracing and accelerated path construction using proxy path tracing, shell tracing, and volumetric path tracing. In proxy path tracing in particular, the rendering application instantiates proxy geometry in the form of a bounding sphere and determines internal scattering in the grain using a precomputed grain scattering distribution function that relates incident and outgoing radiance functions on the bounding sphere. In shell tracing, the rendering application uses shells to aggregate many grain interactions into a single step.Type: GrantFiled: February 8, 2017Date of Patent: January 1, 2019Assignees: Disney Enterprises, Inc., ETH Zurich (Eidgenoessische Technische Hochschule Zurich)Inventors: Jan Novak, Thomas Muller, Marios Papas, Wojciech Jarosz
-
Patent number: 10133171Abstract: A system for augmenting the appearance of an object including a plurality of projectors. Each projector includes a light source and a lens in optical communication with the light source, where the lens focuses light emitted by the light source on the object. The system also includes a computer in communication with the plurality of projectors, the computer including a memory component and a processing element in communication with the memory component and the plurality of projectors. The processing element determines a plurality of images to create an augmented appearance of the object and provides the plurality of images to the plurality of projectors to project light corresponding to the plurality of images onto the object to create the augmented appearance of the object. After the images are projected onto the object, the augmented appearance of the objected is substantially the same regardless of a viewing angle for the object.Type: GrantFiled: March 28, 2016Date of Patent: November 20, 2018Assignees: Disney Enterprises, Inc., ETH Zurich (Eidgenoessische Technische Hochschule Zurich)Inventors: Anselm Grundhofer, Amit Bermano, Bernd Bickel, Philipp Bruschweiler, Markus Gross, Daisuke Iwai
-
Patent number: 10122994Abstract: The present disclosure relates to techniques for reconstructing an object in three dimensions that is captured in a set of two-dimensional images. The object is reconstructed in three dimensions by computing depth values for edges of the object in the set of two-dimensional images. The set of two-dimensional images may be samples of a light field surrounding the object. The depth values may be computed by exploiting local gradient information in the set of two-dimensional images. After computing the depth values for the edges, depth values between the edges may be determined by identifying types of the edges (e.g., a texture edge, a silhouette edge, or other type of edge). Then, the depth values from the set of two-dimensional images may be aggregated in a three-dimensional space using a voting scheme, allowing the reconstruction of the object in three dimensions.Type: GrantFiled: October 31, 2017Date of Patent: November 6, 2018Assignees: DISNEY ENTERPRISES, INC., ETH ZÜRICH (EIDGENÖSSISCHE TECHNISCHE HOCHSCHULE ZÜRICH)Inventors: Kaan Yücer, Changil Kim, Alexander Sorkine-Hornung, Olga Sorkine-Hornung
-
Publication number: 20180315168Abstract: Enhanced removing of noise and outliers from one or more point sets generated by image-based 3D reconstruction techniques is provided. In accordance with the disclosure, input images and corresponding depth maps can be used to remove pixels that are geometrically and/or photometrically inconsistent with the colored surface implied by the input images. This allows standard surface reconstruction methods (such as Poisson surface reconstruction) to perform less smoothing and thus achieve higher quality surfaces with more features. In some implementations, the enhanced point-cloud noise removal in accordance with the disclosure can include computing per-view depth maps, and detecting and removing noisy points and outliers from each per-view point cloud by checking if points are consistent with the surface implied by the other input views.Type: ApplicationFiled: July 6, 2018Publication date: November 1, 2018Applicants: Disney Enterprises, Inc., ETH ZÜRICH (EIDGENÖSSISCHE TECHNISCHE HOCHSCHULE ZÜRICH)Inventors: Changil KIM, Olga SORKINE-HORNUNG, Christopher SCHROERS, Henning ZIMMER, Katja WOLFF, Mario BOTSCH, Alexander SORKINE-HORNUNG
-
Publication number: 20180293711Abstract: Supervised machine learning using convolutional neural network (CNN) is applied to denoising images rendered by MC path tracing. The input image data may include pixel color and its variance, as well as a set of auxiliary buffers that encode scene information (e.g., surface normal, albedo, depth, and their corresponding variances). In some embodiments, a CNN directly predicts the final denoised pixel value as a highly non-linear combination of the input features. In some other embodiments, a kernel-prediction neural network uses a CNN to estimate the local weighting kernels, which are used to compute each denoised pixel from its neighbors. In some embodiments, the input image can be decomposed into diffuse and specular components. The diffuse and specular components are then independently preprocessed, filtered, and postprocessed, before recombining them to obtain a final denoised image.Type: ApplicationFiled: November 15, 2017Publication date: October 11, 2018Applicants: Disney Enterprises, Inc., ETH Zürich (Eidgenössische Technische Hochschule Zürich)Inventors: Thijs Vogels, Jan Novák, Fabrice Rousselle, Brian McWilliams
-
Patent number: 10095953Abstract: Techniques of depth modification for display applications are disclosed. A multiscopic video frame, including at least first and second images depicting a scene, is received. Depth information pertaining to the multiscopic video frame is received. A depth mapping function is determined based on one or more image characteristics of the multiscopic video frame, other than depth. The depth information is modified based on the depth mapping function. At least a third image is generated based on the modified depth information and based further on at least one of the first and second images, where the third image is output for display.Type: GrantFiled: May 28, 2014Date of Patent: October 9, 2018Assignees: Disney Enterprises, Inc., ETH Zurich (Eidgenoessische Technische Hochschule Zurich)Inventors: Aljosa Aleksej Andrej Smolic, Tunc Ozan Aydin, Steven Charles Poulakos, Simon Heinzle, Alexandre Chapiro
-
Patent number: 10091435Abstract: The disclosure provides an approach for image segmentation from an uncalibrated camera array. In one aspect, a segmentation application computes a pseudo depth map for each frame of a video sequence recorded with a camera array based on dense correspondences between cameras in the array. The segmentation application then fuses such pseudo depth maps computed for satellite cameras of the camera array to obtain a pseudo depth map at a central camera. Further, the segmentation application interpolates virtual green screen positions for an entire frame based on user input which provides control points and pseudo depth thresholds at the control points. The segmentation application then computes an initial segmentation based on a thresholding using the virtual green screen positions, and refines the initial segmentation by solving a binary labeling problem in a Markov random field to better align the segmentation with image edges and provide temporal coherency for the segmentation.Type: GrantFiled: June 7, 2016Date of Patent: October 2, 2018Assignees: Disney Enterprises, Inc., ETH Zurich (Eidgenoessische Technische Hochschule Zurich)Inventors: Henning Zimmer, Alexander Sorkine Hornung, Mario Botsch, Federico Perazzi
-
Patent number: 10074160Abstract: Enhanced removing of noise and outliers from one or more point sets generated by image-based 3D reconstruction techniques is provided. In accordance with the disclosure, input images and corresponding depth maps can be used to remove pixels that are geometrically and/or photometrically inconsistent with the colored surface implied by the input images. This allows standard surface reconstruction methods (such as Poisson surface reconstruction) to perform less smoothing and thus achieve higher quality surfaces with more features. In some implementations, the enhanced point-cloud noise removal in accordance with the disclosure can include computing per-view depth maps, and detecting and removing noisy points and outliers from each per-view point cloud by checking if points are consistent with the surface implied by the other input views.Type: GrantFiled: September 30, 2016Date of Patent: September 11, 2018Assignees: DISNEY ENTERPRISES, INC., ETH ZÜRICH (EIDGENÖSSISCHE TECHNISCHE HOCHSCHULE ZÜRICH)Inventors: Changil Kim, Olga Sorkine-Hornung, Christopher Schroers, Henning Zimmer, Katja Wolff, Mario Botsch, Alexander Sorkine-Hornung
-
Publication number: 20180225827Abstract: Embodiments can provide a strategy for controlling information flow both from known opacity regions to unknown regions, as well as within the unknown region itself. This strategy is formulated through the use and refinement of various affinity definitions. As a result of this strategy, a final linear system can be obtained, which can be solved in closed form. One embodiment pertains to identifying opacity information flows. The opacity information flow may include one or more of flows from pixels in the image that have similar colors to a target pixel, flows from pixels in the foreground and background to the target pixel, flows from pixels in the unknown opacity region in the image to the target pixel, flows from pixels immediately surrounding the target pixels in the image to the target pixel, and any other flow.Type: ApplicationFiled: February 2, 2018Publication date: August 9, 2018Applicants: Disney Enterprises, Inc., ETH Zürich (Eidgenössische Technische Hochschule Zürich)Inventors: Yagiz Aksoy, Tunc Ozan Aydin