Nvidia Corporation

Roblox Corporation

Morgan Samuel McGuire

Jonghyun Kim

Michael Stengel

Josef Bo Spjut

Benjamin Boudaoud

Mahesh Kumar Nandwana

David Patrick Luebke

Sanja Fidler

Charles T Loop

Karsten Julian Kreis

Kangxue Yin

Philippe Clavel

Towaki Alan Takikawa

Joey Litalien

Alen Ladavac

Youngmo Jeong

Gerrit Ary Slavenburg

Rouslan Lyubomirov Dimitrov

Kiran Bhat

Rahul P Sathe

Tom J Verbeure

Sau Yan Keith Li

Holger Heinrich Gruen

Joohwan Kim

Lars Nordskog

Seth P Schneider

Adam Christopher Marrs

Cody J Robson

Tom Sanocki

Some implementations relate to methods, systems, and computer-readable media to reproduce a voice stream with removed personally identifiable information (PII). An original voice stream is received from a user by a hardware processor. The original voice stream is converted into text using a machine learning (ML) voice transcription model. Then, the text is used for generating an anonymized voice stream corresponding to the text having similar auditory properties to the original voice stream other than PII using a machine learning (ML) voice synthesis model. The similar properties are determined using metadata corresponding to the original voice stream. The metadata may be obtained by analyzing acoustic characteristics of the original voice stream. The metadata may include volume changes and pitch frequency changes stored as metadata annotations associated with tokens in the text as key-value pairs. The generation may use the metadata annotations to determine the similar audio properties.

Privacy-preserving avatar voice transmission

A computer-implemented method includes receiving, at a server, a first audio stream of a performance associated with a first client device. The method further includes receiving, at the server, a second audio stream of the performance associated with a second client device. The method further includes during a time window of the performance, where the time window is less than a total time of the performance: generating a synthesized first audio stream that predicts a future of the performance based on audio features of the first audio stream and mixing the synthesized first audio stream and the second audio stream to form a combined audio stream that synchronizes the synthesized first audio stream and the second audio stream, where the time window is advanced and the generating and the mixing are repeated until the performance is complete. The method further includes transmitting the combined audio stream to the second client device.

Synthesizing audio for synchronous communication

A computer-implemented method to determine whether to introduce latency into an audio stream from a particular speaker includes an audio stream from a sender device. The method further includes providing, as input to a trained machine-learning model, the audio stream and a speech analysis score, information about one or more voice emotion parameters, and one or more voice emotion scores for a first user associated with the sender device, wherein the trained machine-learning model is iteratively applied to the audio stream and wherein each iteration corresponds to a respective portion of the audio stream. The method further includes generating as output, with the trained machine-learning model, a level of toxicity in the audio stream. The method further includes transmitting the audio stream to a recipient device, wherein the transmitting is performed to introduce a time delay in the audio stream based on the level of toxicity.

Artificial latency for moderating voice communication

In an embodiment, a modular augmented reality display is provided that incorporates prescription eyewear that can be used separately by the wearer. In an embodiment, an image is generated from a removable display attached to the eyewear and directed into the edge of a prescription lens, which acts as a waveguide. The image is internally reflected within the prescription lens, and is directed to the wearer by an image combiner embedded within the prescription lens. In an embodiment, the augmented reality display includes a wearable belt pouch that includes a battery and support electronics connected to the eyewear so that the weight on the eyewear is reduced.

Modular prescription augmented reality display

During the rendering of an image, specific pixels in the image are identified where antialiasing would be helpful. Antialiasing is then performed on these identified pixels, where anti-aliasing is a technique used to add greater realism to a digital image by smoothing jagged edges. This reduces a cost of performing antialiasing by reducing a number of pixels within an image on which antialiasing is performed.

Adding greater realism to a computer-generated image by smoothing jagged edges

Generating polygon meshes that approximate surfaces using root-finding and iteration for mesh vertex positions. In some implementations, a method includes receiving input data that represents a surface that distinguishes an inside and an outside of a volume. A voxel grid that includes the surface is determined, the voxel grid including a plurality of voxels. Particular voxels of the voxel grid are identified, which the surface intersects. A mesh is generated that approximates the surface, the mesh including a plurality of polygons that are defined by vertices in the particular voxels. Generating the mesh includes determining positions of the vertices using a root-finding technique that finds roots of a surface function that describes the surface.

Method and system for generating polygon meshes approximating surfaces using root-finding and iteration for mesh vertex positions

Generating polygon meshes that approximate surfaces using iteration for mesh vertex positions. In some implementations, a method includes receiving input data that represents a surface distinguishing a volume, where a voxel grid includes the surface. Particular voxels of the voxel grid are identified, which the surface intersects. A surface-approximating mesh is generated including polygons defined by vertices in the particular voxels. Generating the mesh includes determining approximate positions of a subset of the vertices in a subset of the particular voxels, based on interpolation of locations in the voxel subset where the surface intersects the voxel subset. Errors between approximate voxel values (based on the approximate positions) and assigned voxel values of the particular voxels (based on the input data) are determined, and the approximate position of at least one vertex of the subset of the vertices is adjusted using a successive over-relaxation technique to reduce the errors.

Method and system for generating polygon meshes approximating surfaces using iteration for mesh vertex positions

Systems and methods are described for rendering complex surfaces or geometry. In at least one embodiment, neural signed distance functions (SDFs) can be used that efficiently capture multiple levels of detail (LODs), and that can be used to reconstruct multi-dimensional geometry or surfaces with high image quality. An example architecture can represent complex shapes in a compressed format with high visual fidelity, and can generalize across different geometries from a single learned example. Extremely small multi-layer perceptrons (MLPs) can be used with an octree-based feature representation for the learned neural SDFs.

Real-time rendering with implicit shapes

A display device for measuring the end-to-end latency of a computing system. The computing system includes an input device, a computing device, and the display device. The display device is directly connected with the input device and receives input data packets generated by the input device in response to received user input events. The display device passes the input packets to the computing device for graphics processing. The display device measures the end-to-end latency comprising the sum of three latencies. A first latency comprises an input delay of the input device. A second latency comprises an amount of time between generation of the input packet and a corresponding change in pixel values caused by the input event at the display device. A third latency comprises a display latency. The display device also displays latency information associated with the measured end-to-end latency.

System-latency-aware display device

An augmented reality display system includes a first beam path for a foveal inset image on a holographic optical element, a second beam path for a peripheral display image on the holographic optical element, and pupil position tracking logic that generates control signals to set a position of the foveal inset as perceived through the holographic optical element, to determine the peripheral display image, and to control a moveable stage.

Foveated display for augmented reality

In an embodiment, an augmented reality display provides an expanded eye box and enlarged field of view through the use of holographic optical elements. In at least one example, an incoupling element directs an image into a waveguide, which transmits the image to a set of outcoupling gratings. In one example, a set of holographic optical elements opposite the outcoupling elements reflect the image to the user with an enlarged field of view while maintaining an expanded eye box.

Growing community of inventors

Waterloo, Canada

Morgan Samuel McGuire