Patents by Inventor Timo Oskari Aila
Timo Oskari Aila 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: 20240161250Abstract: Techniques are disclosed herein for generating a content item. The techniques include performing one or more first denoising operations based on an input and a first machine learning model to generate a first content item, and performing one or more second denoising operations based on the input, the first content item, and a second machine learning model to generate a second content item, where the first machine learning model is trained to denoise content items having an amount of corruption within a first corruption range, the second machine learning model is trained to denoise content items having an amount of corruption within a second corruption range, and the second corruption range is lower than the first corruption range.Type: ApplicationFiled: October 11, 2023Publication date: May 16, 2024Inventors: Yogesh BALAJI, Timo Oskari AILA, Miika AITTALA, Bryan CATANZARO, Xun HUANG, Tero Tapani KARRAS, Karsten KREIS, Samuli LAINE, Ming-Yu LIU, Seungjun NAH, Jiaming SONG, Arash VAHDAT, Qinsheng ZHANG
-
Publication number: 20240144001Abstract: A method and system are disclosed for training a model that implements a machine-learning algorithm. The technique utilizes latent descriptor vectors to change a multiple-valued output problem into a single-valued output problem and includes the steps of receiving a set of training data, processing, by a model, the set of training data to generate a set of output vectors, and adjusting a set of model parameters and component values for at least one latent descriptor vector in the plurality of latent descriptor vectors based on the set of output vectors. The set of training data includes a plurality of input vectors and a plurality of desired output vectors, and each input vector in the plurality of input vectors is associated with a particular latent descriptor vector in a plurality of latent descriptor vectors. Each latent descriptor vector comprises a plurality of scalar values that are initialized prior to training the model.Type: ApplicationFiled: May 5, 2023Publication date: May 2, 2024Inventors: Tero Tapani Karras, Timo Oskari Aila, Samuli Matias Laine
-
Patent number: 11861890Abstract: A style-based generative network architecture enables scale-specific control of synthesized output data, such as images. During training, the style-based generative neural network (generator neural network) includes a mapping network and a synthesis network. During prediction, the mapping network may be omitted, replicated, or evaluated several times. The synthesis network may be used to generate highly varied, high-quality output data with a wide variety of attributes. For example, when used to generate images of people's faces, the attributes that may vary are age, ethnicity, camera viewpoint, pose, face shape, eyeglasses, colors (eyes, hair, etc.), hair style, lighting, background, etc. Depending on the task, generated output data may include images, audio, video, three-dimensional (3D) objects, text, etc.Type: GrantFiled: January 20, 2023Date of Patent: January 2, 2024Assignee: NVIDIA CorporationInventors: Tero Tapani Karras, Timo Oskari Aila, Samuli Matias Laine
-
Publication number: 20230368073Abstract: Techniques are disclosed herein for generating a content item. The techniques include receiving a content item and metadata indicating a level of corruption associated with the content item; and for each iteration included in a plurality of iterations: performing one or more operations to add corruption to a first version of the content item to generate a second version of the content item, and performing one or more operations to reduce corruption in the second version of the content item to generate a third version of the content item, wherein a level of corruption associated with the third version of the content item is less than a level of corruption associated with the first version of the content item.Type: ApplicationFiled: March 10, 2023Publication date: November 16, 2023Inventors: Tero Tapani KARRAS, Miika AITTALA, Timo Oskari AILA, Samuli LAINE
-
Publication number: 20230368337Abstract: Techniques are disclosed herein for generating a content item. The techniques include receiving a content item and metadata indicating a level of corruption associated with the content item; and for each iteration included in a plurality of iterations: performing one or more operations to add corruption to a first version of the content item to generate a second version of the content item, and performing one or more operations to reduce corruption in the second version of the content item to generate a third version of the content item, wherein a level of corruption associated with the third version of the content item is less than a level of corruption associated with the first version of the content item.Type: ApplicationFiled: March 10, 2023Publication date: November 16, 2023Inventors: Tero Tapani KARRAS, Miika AITTALA, Timo Oskari AILA, Samuli LAINE
-
Patent number: 11775829Abstract: A latent code defined in an input space is processed by the mapping neural network to produce an intermediate latent code defined in an intermediate latent space. The intermediate latent code may be used as appearance vector that is processed by the synthesis neural network to generate an image. The appearance vector is a compressed encoding of data, such as video frames including a person's face, audio, and other data. Captured images may be converted into appearance vectors at a local device and transmitted to a remote device using much less bandwidth compared with transmitting the captured images. A synthesis neural network at the remote device reconstructs the images for display.Type: GrantFiled: December 12, 2022Date of Patent: October 3, 2023Assignee: NVIDIA CorporationInventors: Tero Tapani Karras, Samuli Matias Laine, David Patrick Luebke, Jaakko T. Lehtinen, Miika Samuli Aittala, Timo Oskari Aila, Ming-Yu Liu, Arun Mohanray Mallya, Ting-Chun Wang
-
Patent number: 11763168Abstract: A generative adversarial neural network (GAN) learns a particular task by being shown many examples. In one scenario, a GAN may be trained to generate new images including specific objects, such as human faces, bicycles, etc. Rather than training a complex GAN having a predetermined topology of features and interconnections between the features to learn the task, the topology of the GAN is modified as the GAN is trained for the task. The topology of the GAN may be simple in the beginning and become more complex as the GAN learns during the training, eventually evolving to match the predetermined topology of the complex GAN. In the beginning the GAN learns large-scale details for the task (bicycles have two wheels) and later, as the GAN becomes more complex, learns smaller details (the wheels have spokes).Type: GrantFiled: January 3, 2022Date of Patent: September 19, 2023Assignee: NVIDIA CorporationInventors: Tero Tapani Karras, Timo Oskari Aila, Samuli Matias Laine, Jaakko T. Lehtinen
-
Patent number: 11734890Abstract: A three-dimensional (3D) model of an object is recovered from two-dimensional (2D) images of the object. Each image in the set of 2D images includes the object captured from a different camera position and deformations of a base mesh that defines the 3D model may be computed corresponding to each image. The 3D model may also include a texture map that represents the lighting and material properties of the 3D model. Recovery of the 3D model relies on analytic antialiasing to provide a link between pixel colors in the 2D images and geometry of the 3D model. A modular differentiable renderer design yields high performance by leveraging existing, highly optimized hardware graphics pipelines to reconstruct the 3D model. The differential renderer renders images of the 3D model and differences between the rendered images and reference images are propagated backwards through the rendering pipeline to iteratively adjust the 3D model.Type: GrantFiled: February 15, 2021Date of Patent: August 22, 2023Assignee: NVIDIA CorporationInventors: Samuli Matias Laine, Janne Johannes Hellsten, Tero Tapani Karras, Yeongho Seol, Jaakko T. Lehtinen, Timo Oskari Aila
-
Patent number: 11694072Abstract: A method and system are disclosed for training a model that implements a machine-learning algorithm. The technique utilizes latent descriptor vectors to change a multiple-valued output problem into a single-valued output problem and includes the steps of receiving a set of training data, processing, by a model, the set of training data to generate a set of output vectors, and adjusting a set of model parameters and component values for at least one latent descriptor vector in the plurality of latent descriptor vectors based on the set of output vectors. The set of training data includes a plurality of input vectors and a plurality of desired output vectors, and each input vector in the plurality of input vectors is associated with a particular latent descriptor vector in a plurality of latent descriptor vectors. Each latent descriptor vector comprises a plurality of scalar values that are initialized prior to training the model.Type: GrantFiled: November 29, 2017Date of Patent: July 4, 2023Assignee: NVIDIA CorporationInventors: Tero Tapani Karras, Timo Oskari Aila, Samuli Matias Laine
-
Patent number: 11682199Abstract: A style-based generative network architecture enables scale-specific control of synthesized output data, such as images. During training, the style-based generative neural network (generator neural network) includes a mapping network and a synthesis network. During prediction, the mapping network may be omitted, replicated, or evaluated several times. The synthesis network may be used to generate highly varied, high-quality output data with a wide variety of attributes. For example, when used to generate images of people's faces, the attributes that may vary are age, ethnicity, camera viewpoint, pose, face shape, eyeglasses, colors (eyes, hair, etc.), hair style, lighting, background, etc. Depending on the task, generated output data may include images, audio, video, three-dimensional (3D) objects, text, etc.Type: GrantFiled: August 23, 2022Date of Patent: June 20, 2023Assignee: NVIDIA CorporationInventors: Tero Tapani Karras, Timo Oskari Aila, Samuli Matias Laine
-
Publication number: 20230186617Abstract: A style-based generative network architecture enables scale-specific control of synthesized output data, such as images. During training, the style-based generative neural network (generator neural network) includes a mapping network and a synthesis network. During prediction, the mapping network may be omitted, replicated, or evaluated several times. The synthesis network may be used to generate highly varied, high-quality output data with a wide variety of attributes. For example, when used to generate images of people’s faces, the attributes that may vary are age, ethnicity, camera viewpoint, pose, face shape, eyeglasses, colors (eyes, hair, etc.), hair style, lighting, background, etc. Depending on the task, generated output data may include images, audio, video, three-dimensional (3D) objects, text, etc.Type: ApplicationFiled: January 20, 2023Publication date: June 15, 2023Inventors: Tero Tapani Karras, Timo Oskari Aila, Samuli Matias Laine
-
Publication number: 20230110206Abstract: A latent code defined in an input space is processed by the mapping neural network to produce an intermediate latent code defined in an intermediate latent space. The intermediate latent code may be used as appearance vector that is processed by the synthesis neural network to generate an image. The appearance vector is a compressed encoding of data, such as video frames including a person's face, audio, and other data. Captured images may be converted into appearance vectors at a local device and transmitted to a remote device using much less bandwidth compared with transmitting the captured images. A synthesis neural network at the remote device reconstructs the images for display.Type: ApplicationFiled: December 12, 2022Publication date: April 13, 2023Inventors: Tero Tapani Karras, Samuli Matias Laine, David Patrick Luebke, Jaakko T. Lehtinen, Miika Samuli Aittala, Timo Oskari Aila, Ming-Yu Liu, Arun Mohanray Mallya, Ting-Chun Wang
-
Patent number: 11625613Abstract: A latent code defined in an input space is processed by the mapping neural network to produce an intermediate latent code defined in an intermediate latent space. The intermediate latent code may be used as appearance vector that is processed by the synthesis neural network to generate an image. The appearance vector is a compressed encoding of data, such as video frames including a person's face, audio, and other data. Captured images may be converted into appearance vectors at a local device and transmitted to a remote device using much less bandwidth compared with transmitting the captured images. A synthesis neural network at the remote device reconstructs the images for display.Type: GrantFiled: January 7, 2021Date of Patent: April 11, 2023Assignee: NVIDIA CorporationInventors: Tero Tapani Karras, Samuli Matias Laine, David Patrick Luebke, Jaakko T. Lehtinen, Miika Samuli Aittala, Timo Oskari Aila, Ming-Yu Liu, Arun Mohanray Mallya, Ting-Chun Wang
-
Patent number: 11620521Abstract: A style-based generative network architecture enables scale-specific control of synthesized output data, such as images. During training, the style-based generative neural network (generator neural network) includes a mapping network and a synthesis network. During prediction, the mapping network may be omitted, replicated, or evaluated several times. The synthesis network may be used to generate highly varied, high-quality output data with a wide variety of attributes. For example, when used to generate images of people's faces, the attributes that may vary are age, ethnicity, camera viewpoint, pose, face shape, eyeglasses, colors (eyes, hair, etc.), hair style, lighting, background, etc. Depending on the task, generated output data may include images, audio, video, three-dimensional (3D) objects, text, etc.Type: GrantFiled: January 28, 2021Date of Patent: April 4, 2023Assignee: NVIDIA CorporationInventors: Tero Tapani Karras, Samuli Matias Laine, Jaakko T. Lehtinen, Miika Samuli Aittala, Janne Johannes Hellsten, Timo Oskari Aila
-
Patent number: 11610122Abstract: A latent code defined in an input space is processed by the mapping neural network to produce an intermediate latent code defined in an intermediate latent space. The intermediate latent code may be used as appearance vector that is processed by the synthesis neural network to generate an image. The appearance vector is a compressed encoding of data, such as video frames including a person's face, audio, and other data. Captured images may be converted into appearance vectors at a local device and transmitted to a remote device using much less bandwidth compared with transmitting the captured images. A synthesis neural network at the remote device reconstructs the images for display.Type: GrantFiled: January 7, 2021Date of Patent: March 21, 2023Assignee: NVIDIA CorporationInventors: Tero Tapani Karras, Samuli Matias Laine, David Patrick Luebke, Jaakko T. Lehtinen, Miika Samuli Aittala, Timo Oskari Aila, Ming-Yu Liu, Arun Mohanray Mallya, Ting-Chun Wang
-
Patent number: 11610435Abstract: A latent code defined in an input space is processed by the mapping neural network to produce an intermediate latent code defined in an intermediate latent space. The intermediate latent code may be used as appearance vector that is processed by the synthesis neural network to generate an image. The appearance vector is a compressed encoding of data, such as video frames including a person's face, audio, and other data. Captured images may be converted into appearance vectors at a local device and transmitted to a remote device using much less bandwidth compared with transmitting the captured images. A synthesis neural network at the remote device reconstructs the images for display.Type: GrantFiled: October 13, 2020Date of Patent: March 21, 2023Assignee: NVIDIA CorporationInventors: Tero Tapani Karras, Samuli Matias Laine, David Patrick Luebke, Jaakko T. Lehtinen, Miika Samuli Aittala, Timo Oskari Aila, Ming-Yu Liu, Arun Mohanray Mallya, Ting-Chun Wang
-
Patent number: 11605217Abstract: A style-based generative network architecture enables scale-specific control of synthesized output data, such as images. During training, the style-based generative neural network (generator neural network) includes a mapping network and a synthesis network. During prediction, the mapping network may be omitted, replicated, or evaluated several times. The synthesis network may be used to generate highly varied, high-quality output data with a wide variety of attributes. For example, when used to generate images of people's faces, the attributes that may vary are age, ethnicity, camera viewpoint, pose, face shape, eyeglasses, colors (eyes, hair, etc.), hair style, lighting, background, etc. Depending on the task, generated output data may include images, audio, video, three-dimensional (3D) objects, text, etc.Type: GrantFiled: December 28, 2020Date of Patent: March 14, 2023Assignee: NVIDIA CorporationInventors: Tero Tapani Karras, Timo Oskari Aila, Samuli Matias Laine
-
Patent number: 11605001Abstract: A style-based generative network architecture enables scale-specific control of synthesized output data, such as images. During training, the style-based generative neural network (generator neural network) includes a mapping network and a synthesis network. During prediction, the mapping network may be omitted, replicated, or evaluated several times. The synthesis network may be used to generate highly varied, high-quality output data with a wide variety of attributes. For example, when used to generate images of people's faces, the attributes that may vary are age, ethnicity, camera viewpoint, pose, face shape, eyeglasses, colors (eyes, hair, etc.), hair style, lighting, background, etc. Depending on the task, generated output data may include images, audio, video, three-dimensional (3D) objects, text, etc.Type: GrantFiled: January 28, 2021Date of Patent: March 14, 2023Assignee: NVIDIA CorporationInventors: Tero Tapani Karras, Samuli Matias Laine, Jaakko T. Lehtinen, Miika Samuli Aittala, Janne Johannes Hellsten, Timo Oskari Aila
-
Patent number: 11580395Abstract: A latent code defined in an input space is processed by the mapping neural network to produce an intermediate latent code defined in an intermediate latent space. The intermediate latent code may be used as appearance vector that is processed by the synthesis neural network to generate an image. The appearance vector is a compressed encoding of data, such as video frames including a person's face, audio, and other data. Captured images may be converted into appearance vectors at a local device and transmitted to a remote device using much less bandwidth compared with transmitting the captured images. A synthesis neural network at the remote device reconstructs the images for display.Type: GrantFiled: October 13, 2020Date of Patent: February 14, 2023Assignee: NVIDIA CorporationInventors: Tero Tapani Karras, Samuli Matias Laine, David Patrick Luebke, Jaakko T. Lehtinen, Miika Samuli Aittala, Timo Oskari Aila, Ming-Yu Liu, Arun Mohanray Mallya, Ting-Chun Wang
-
Publication number: 20220405880Abstract: Systems and methods are disclosed that improve output quality of any neural network, particularly an image generative neural network. In the real world, details of different scale tend to transform hierarchically. For example, moving a person's head causes the nose to move, which in turn moves the skin pores on the nose. Conventional generative neural networks do not synthesize images in a natural hierarchical manner: the coarse features seem to mainly control the presence of finer features, but not the precise positions of the finer features. Instead, much of the fine detail appears to be fixed to pixel coordinates which is a manifestation of aliasing. Aliasing breaks the illusion of a solid and coherent object moving in space. A generative neural network with reduced aliasing provides an architecture that exhibits a more natural transformation hierarchy, where the exact sub-pixel position of each feature is inherited from underlying coarse features.Type: ApplicationFiled: December 27, 2021Publication date: December 22, 2022Inventors: Tero Tapani Karras, Miika Samuli Aittala, Samuli Matias Laine, Erik Andreas Härkönen, Janne Johannes Hellsten, Jaakko T. Lehtinen, Timo Oskari Aila