DENOISING MONTE CARLO RENDERINGS USING PROGRESSIVE NEURAL NETWORKS
Granted: June 11, 2020
Application Number:
20200184605
Supervised machine learning using neural networks is applied to denoising images rendered by MC path tracing. Specialization of neural networks may be achieved by using a modular design that allows reusing trained components in different networks and facilitates easy debugging and incremental building of complex structures. Specialization may also be achieved by using progressive neural networks. In some embodiments, training of a neural-network based denoiser may use importance…
ADAPTIVE SAMPLING IN MONTE CARLO RENDERINGS USING ERROR-PREDICTING NEURAL NETWORKS
Granted: June 11, 2020
Application Number:
20200184313
A modular architecture is provided for denoising Monte Carlo renderings using neural networks. The temporal approach extracts and combines feature representations from neighboring frames rather than building a temporal context using recurrent connections. A multiscale architecture includes separate single-frame or temporal denoising modules for individual scales, and one or more scale compositor neural networks configured to adaptively blend individual scales. An error-predicting module…
DENOISING MONTE CARLO RENDERINGS USING MACHINE LEARNING WITH IMPORTANCE SAMPLING
Granted: May 7, 2020
Application Number:
20200143522
Supervised machine learning using neural networks is applied to denoising images rendered by MC path tracing. Specialization of neural networks may be achieved by using a modular design that allows reusing trained components in different networks and facilitates easy debugging and incremental building of complex structures. Specialization may also be achieved by using progressive neural networks. In some embodiments, training of a neural-network based denoiser may use importance…
MACHINE LEARNING BASED VIDEO COMPRESSION
Granted: March 19, 2020
Application Number:
20200090069
Systems and methods for compressing target content are disclosed. In one embodiment, a system may include non-transient electronic storage and one or more physical computer processors. The one or more physical computer processors may be configured by machine-readable instructions to obtain the target content comprising one or more frames, wherein a given frame comprises one or more features. The one or more physical computer processors may be configured by machine-readable instructions…
SYSTEMS AND METHODS FOR TRACKING A PHYSICAL OBJECT USING A PASSIVE OBJECT HAVING A REFLECTIVE SURFACE
Granted: March 19, 2020
Application Number:
20200086208
Systems, methods, and devices are disclosed for tracking physical objects using a passive reflective object. A computer-implemented method includes obtaining a location profile derived from content capturing a passive object having a reflective surface reflecting one or more real-world objects. The passive object is attached to a physical object. The method further includes transmitting the location profile to a simulation device. The method further includes generating a virtual…
TECHNIQUES FOR CAPTURING DYNAMIC APPEARANCE OF SKIN
Granted: March 12, 2020
Application Number:
20200082572
Embodiments of the present disclosure techniques for modeling and capturing the dynamic appearance of skin. These techniques can couple dynamic reflectance parameters for skin (albedo and specular reflectance) with dynamic geometry. The disclosed techniques allow for capture and modeling of the dynamic appearance of skin for an actor. The techniques can re-render the actor's face accurately to accurately model the appearance of skin including the albedo of skin that can change primarily…
MACHINE LEARNING BASED VIDEO COMPRESSION
Granted: February 13, 2020
Application Number:
20200053388
Systems and methods are disclosed for compressing a target video. A computer-implemented method may use a computer system that include one or more physical computer processors and non-transient electronic storage. The computer-implemented method may include: obtaining the target video, extracting one or more frames from the target video, and generating an estimated optical flow based on a displacement of pixels between the one or more frames. The one or more frames may include one or…
PIPELINE FOR HIGH DYNAMIC RANGE VIDEO CODING BASED ON LUMINANCE INDEPENDENT CHROMATICITY PREPROCESSING
Granted: February 13, 2020
Application Number:
20200053252
The disclosure describes a high dynamic range video coding pipeline that may reduce color artifacts and improve compression efficiency. The disclosed pipeline separates the luminance component from the chrominance components of an input signal (e.g., an RGB source video) and applies a scaling of the chrominance components before encoding, thereby reducing perceivable color artifacts while maintaining luminance quality.
KERNEL-PREDICTING CONVOLUTIONAL NEURAL NETWORKS FOR DENOISING
Granted: January 23, 2020
Application Number:
20200027198
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…
COLLABORATIVE AI STORYTELLING
Granted: January 16, 2020
Application Number:
20200019370
Implementations of the disclosure describe AI systems that offer an improvisational story telling AI agent that may interact collaboratively with a user. In one implementation, a story telling device may be implemented using i) a natural language understanding (NLU) component to process human language input (e.g., digitized speech or text input); ii) a natural language processing (NLP) component to parse the human language input into a story segment or sequence; iii) a component for…
METHOD AND SYSTEM FOR ENCODING AND TRANSMITTING HIGH DEFINITION 3-D MULTIMEDIA CONTENT
Granted: January 9, 2020
Application Number:
20200014954
One particular implementation may take the form of a method and system for decoding 3-D multimedia content. In one example, the present invention may take the form of a method of decoding 3-D multimedia content encoded with at least content frames and null frames. The method may operate to receive the 3-D multimedia content, extract at least one content frame, at least one null frame, and display information. The method may further operate to reconstruct the content and null frames in a…
ORDERED MAPPING ON A THREE-DIMENSIONAL PROJECTION SURFACE
Granted: January 2, 2020
Application Number:
20200005688
Systems and methods are provided for presenting visual media on a structure having a plurality of unordered light sources, e.g., fiber optic light sources, light emitting diodes (LEDs), etc. Visual media can be created based on a computer model of the structure. Images of the structure can be analyzed to determine the location of each of the light sources. A lookup table can be generated based on the image analysis, and used to correlate pixels of the visual media to one or more of the…
SYSTEMS AND METHODS FOR PRESENTING AN INTERACTIVE NARRATIVE
Granted: December 19, 2019
Application Number:
20190384826
Systems, devices, and methods are disclosed for presenting an interactive narrative. An apparatus includes a user interface. The apparatus also includes one or more processors operatively coupled to the user interface and a non-transitory computer-readable medium. The non-transitory computer-readable medium stores instructions that, when executed, cause the one or more processors to present a first piece of content corresponding to a given narrative via the user interface. The given…
SEE-THROUGH OPERATOR AWARENESS TOOL USING SYNTHESIZED VIEWPOINTS
Granted: December 12, 2019
Application Number:
20190379878
The disclosure is directed to providing operator visibility through an object that occludes the view of the operator by using a HMD system in communication with one or more imaging devices. A method of doing so may include: using one or more imaging devices coupled to an exterior of an object to capture image data of a real-world environment surrounding the object: calculating an orientation of a HMD positioned in an interior of the object; using at least the calculated orientation of…
SYSTEMS AND METHODS FOR CORRECTING COLOR FOR UNCALIBRATED MATERIALS
Granted: December 5, 2019
Application Number:
20190370939
Systems and methods for correcting color of uncalibrated material is disclosed. Example embodiments include a system to correct color of uncalibrated material. The system may include a non-transitory computer-readable medium operatively coupled to processors. The non-transitory computer-readable medium may store instructions that, when executed cause the processors to perform a number of operations. One operation is to obtain a target image of a degraded target material with one or more…
LEVERAGING MICROSERVICES TO ORCHESTRATE MEDIA WORKFLOWS IN THE CLOUD
Granted: November 28, 2019
Application Number:
20190364081
A method and system provide the ability to orchestrate a media workflow using a computer system. A payload for an application programming interface (API) to be utilized to process media content is determined. The payload is parsed to display one or more variables of the payload in a graphical user interface. The variables are mapped to webform user interface elements. A job of the media workflow is executed. During execution, a webform of the user interface elements is programmatically…
SYSTEMS AND METHODS FOR REAL-TIME COMPOSITING OF VIDEO CONTENT
Granted: November 7, 2019
Application Number:
20190342472
Systems, devices, and methods are disclosed for compositing real-time, real-world video with virtual objects. An electronic device includes circuitry coupled to a memory storing instructions that, when executed, cause the circuitry to receive video of a given video capture region. The circuitry is caused to receive location information and camera information from the unmanned vehicle. The circuitry is caused to obtain a representation of a location of interest corresponding to the…
MACHINE LEARNING ENABLED EVALUATION SYSTEMS AND METHODS
Granted: November 7, 2019
Application Number:
20190340659
Systems and methods for providing machine-learning enabled user-specific evaluations are disclosed. Implementations include obtaining a first set of evaluation data from a user interface, obtaining a first set of target-descriptive data including target-specific characteristics objectively describing the evaluation targets, and training, with a machine-learning algorithm, a user-specific evaluation profile indicating evaluation patterns relative to the first set of evaluation data and…
SYSTEM AND METHOD FOR IDENTIFYING AND TAGGING ASSETS WITHIN AN AV FILE
Granted: October 31, 2019
Application Number:
20190332829
A system for identifying, tagging, and displaying one or more assets within an audio visual (AV) file includes an asset tagging server, an asset tag acquisition device, and a database, wherein the asset tag acquisition device includes an asset identification engine configured to receive an asset identification data set and generate an asset tag data file that includes an asset tag corresponding to each asset. The asset tagging server is configured to receive, from an AV capture device,…
SYSTEMS AND METHODS FOR DISTORTION REMOVAL AT MULTIPLE QUALITY LEVELS
Granted: October 31, 2019
Application Number:
20190333190
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.…
