Nvidia Corporation

Mitsubishi Electric Research Laboratories, Inc.

Nvidia Corporaton

Ming-Yu Liu

Jan Kautz

Oncel C Tuzel

Arun Mohanray Mallya

Ting-Chun Wang

Deqing Sun

Xiaodong Yang

Samuli Matias Laine

David Patrick Luebke

Timo Oskari Aila

Tero Tapani Karras

Yuichi Taguchi

Ming-Hsuan Yang

Jaakko Tapani Lehtinen

Miika Samuli Aittala

Srikumar Ramalingam

Sanja Fidler

Varun Jampani

Jinwei Gu

Yi-Hsuan Tsai

Jun Gao

Orazio Gallo

Kangxue Yin

Teng-Yok Lee

Karan Sapra

Xitong Yang

Raviteja Vemulapalli

Aurobinda Maharana

Wei-Chih Tu

Chieh-Chi Kao

Fanyi Xiao

Alexander Georg Keller

Karl Berntorp

Kihwan Kim

Yijun Li

Arvind Raghunathan

Dieter Fox

Avishai Weiss

John R Zedlewski

Jonathan Tremblay

Sifei Liu

Chen Feng

Alejandro Jose Troccoli

Pradeep Sen

David Jesus Acuna Marrero

Arash Vahdat

Antonio Torralba Barriuso

Zhiding Yu

Amlan Kar

Cuneyt Oncel Tuzel

Aayush Prakash

Seung-Hwan Baek

Abhijit Patait

Amir Massoud Farahmand

Huaijin Chen

Zekun Hao

Aysegul Dundar

Tianchang Shen

Alex John Bauld Evans

Philip Ammirato

Vignesh Ungrapalli

Chen-Hsuan Lin

Thomas Müller-Höhne

Jose Rafael Valle Da Costa

Tim Brooks

Tero Karras

Jaakko Lehtinen

Kevin Lin

Siddharth Gururani

Sergey Tulyakov

Zhongheng Ren

Kota Hara

Kilho Son

Abhishek Sharma

Changhyun Choi

Zhaoshuo Li

Donghoon Lee

One embodiment of a method includes applying a first generator model to a semantic representation of an image to generate an affine transformation, where the affine transformation represents a bounding box associated with at least one region within the image. The method further includes applying a second generator model to the affine transformation and the semantic representation to generate a shape of an object. The method further includes inserting the object into the image based on the bounding box and the shape.

Context-aware synthesis and placement of object instances

Apparatuses, systems, and techniques to determine orientation of an objects in an image. In at least one embodiment, images are processed using a neural network trained to determine orientation of an object.

Determining object orientation from an image with machine learning

Apparatuses, systems, and techniques to detect object in images including digital representations of those objects. In at least one embodiment, one or more objects are detected in an image based, at least in part, on one or more pseudo-labels corresponding to said one or more objects.

Weakly-supervised object detection using one or more neural networks

Apparatuses, systems, and techniques are presented to synthesize consistent images or video. In at least one embodiment, one or more neural networks are used to generate one or more second images based, at least in part, on one or more point cloud representations of one or more first images.

Video synthesis using one or more neural networks

In various examples, a deep three-dimensional (3D) conditional generative model is implemented that can synthesize high resolution 3D shapes using simple guides—such as coarse voxels, point clouds, etc.—by marrying implicit and explicit 3D representations into a hybrid 3D representation. The present approach may directly optimize for the reconstructed surface, allowing for the synthesis of finer geometric details with fewer artifacts. The systems and methods described herein may use a deformable tetrahedral grid that encodes a discretized signed distance function (SDF) and a differentiable marching tetrahedral layer that converts the implicit SDF representation to an explicit surface mesh representation. This combination allows joint optimization of the surface geometry and topology as well as generation of the hierarchy of subdivisions using reconstruction and adversarial losses defined explicitly on the surface mesh.

Synthesizing high resolution 3D shapes from lower resolution representations for synthetic data generation systems and applications

Apparatuses, systems, and techniques to generate pixels based on other pixels. In at least one embodiment, one or more neural networks are used to generate one or more pixels based, at least in part, on sets of pixels surrounding the one or more pixels.

Neural networks to generate pixels

Apparatuses, systems, and techniques are presented to generate images. In at least one embodiment, one or more neural networks are used to generate one or more images based, at least in part, upon one or more semantic features projected from a three-dimensional environment.

Generating images of virtual environments using one or more neural networks

Apparatuses, systems, and techniques are presented to generate digital content. In at least one embodiment, one or more neural networks are used to generate video information based at least in part upon voice information and a combination of image features and facial landmarks corresponding to one or more images of a person.

Speech-driven animation using one or more neural networks

Apparatuses, systems, and techniques to transfer grammar between sentences. In at least one embodiment, one or more first sentences are translated into one or more second sentences having different grammar using one or more neural networks.

Grammar transfer using one or more neural networks

Apparatuses, systems, and techniques are presented to reconstruct one or more images. In at least one embodiment, one or more neural networks are used to generate one or more images of one or more objects based, at least in part, on input indicating motion of the one or more objects.

Generating images of object motion using one or more neural networks

In at least one embodiment, differentiable neural architecture search and reinforcement learning are combined under one framework to discover network architectures with desired properties such as high accuracy, low latency, or both. In at least one embodiment, an objective function for search based on generalization error prevents the selection of architectures prone to overfitting.

Machine-learning-based architecture search method for a neural network

Systems and methods herein address reference frame selection in video streaming applications using one or more processing units to identify a frame of a sequence of frames as a blurred frame based at least in part on a first variance of motion (VoM) of the frame being less than or equal to an adaptive threshold that is based in part on a moving average of variance of motion (MAoV) determined using one or more reference frames.

Frame selection for streaming applications

Systems and methods herein address reference frame selection in video streaming applications using one or more processing units to decode a frame of an encoded video stream that uses an inter-frame depicting an object and an intra-frame depicting the object, the intra-frame being included in a set of intra-frames based at least in part on at least one attribute of the object as depicted in the intra-frame being different from the at least one attribute of the object as depicted in other intra-frames of the set of intra-frames.

Growing community of inventors

Sunnyvale, CA, United States of America

Ming-Yu Liu