NVIDIA Corporation patent applications on August 15th, 2024
Patent Applications by NVIDIA Corporation on August 15th, 2024
NVIDIA Corporation: 10 patent applications
NVIDIA Corporation has applied for patents in the areas of G06F9/50 (3), G06F13/42 (2), G01S17/931 (2), G01S17/89 (2), B60W60/00 (2) G06F9/4881 (1), G06F9/5016 (1), G06F9/5072 (1), G06F13/4282 (1), G06T5/60 (1)
With keywords such as: data, environment, generate, image, training, techniques, neural, surface, systems, and based in patent application abstracts.
Patent Applications by NVIDIA Corporation
20240272943. SYSTEM TASK MANAGEMENT FOR COMPUTING SYSTEMS_simplified_abstract_(nvidia corporation)
Inventor(s): Ashutosh Tadkase of Los Altos Hills CA (US) for nvidia corporation, Akash Bellubbi of San Jose CA (US) for nvidia corporation, Ian Tramble of Mountain View CA (US) for nvidia corporation, Peter Boonstoppel of Pleasanton CA (US) for nvidia corporation, Suraj Das of Santa Clara CA (US) for nvidia corporation, Ranvijay Singh of Santa Clara CA (US) for nvidia corporation, Sever Topan of Burnaby (CA) for nvidia corporation, Albert Davies of San Jose CA (US) for nvidia corporation, Linda Xiong of Milpitas CA (US) for nvidia corporation, Sharat Janapareddy of San Jose CA (US) for nvidia corporation, Ashkan Vafaee of Austin TX (US) for nvidia corporation, Sai Gurrappadi of Santa Clara CA (US) for nvidia corporation, Pulkit Desai of San Jose CA (US) for nvidia corporation, John Lore of San Jose CA (US) for nvidia corporation, Michael Cox of Menlo Park CA (US) for nvidia corporation, Ian Howson of Santa Clara CA (US) for nvidia corporation
IPC Code(s): G06F9/48, G06F9/30, G06F9/38, G06F9/50, G06F9/54, G06F11/07, G06F21/52
CPC Code(s): G06F9/4881
Abstract: one or more embodiments of the present disclosure relate to executing, by a plurality of compute engines, a plurality of runnables of a computing application based at least on an execution schedule and a set of commands associated with the execution schedule. the execution schedule may be generated using a compiling system to include the set of commands. the set of commands may include one or more individual commands corresponding to one or more timing fences dictating a timing and order of execution of one or more individual runnables of the plurality of runnables.
Inventor(s): Shirish Bahirat of Longmont CO (US) for nvidia corporation
IPC Code(s): G06F9/50, G06F13/42
CPC Code(s): G06F9/5016
Abstract: apparatuses, systems, and techniques that allocate volatile memory associated with a particular processor and/or device to one or more other processors. at least one embodiment pertains to maintaining a memory map of volatile memory allocated to a plurality of processors.
Inventor(s): Shirish Bahirat of Longmont CO (US) for nvidia corporation
IPC Code(s): G06F9/50
CPC Code(s): G06F9/5072
Abstract: apparatuses, systems, and techniques to implement a cluster operating system that may control at least a portion of functionality provided by local operating systems executing on one or more computing systems within a distributed computing system. at least one embodiment pertains to methods of the distributed system operating system receiving a service request from an application and providing the service or causing the service to be provided to the application according to various novel techniques described herein.
Inventor(s): Kiran Kumar Modukuri of Santa Clara CA (US) for nvidia corporation, Christopher J. Newburn of South Beloit IL (US) for nvidia corporation, Saptarshi Sen of San Jose CA (US) for nvidia corporation, Akilesh Kailash of San Jose CA (US) for nvidia corporation, Sandeep Joshi of Campbell CA (US) for nvidia corporation
IPC Code(s): G06F13/42, G06F13/28, G06F13/40, G06F15/173
CPC Code(s): G06F13/4282
Abstract: apparatuses, systems, and techniques to route data transfers between hardware devices. in at least one embodiment, a path over which to transfer data from a first hardware component of a computer system to a second hardware component of a computer system is determined based, at least in part, on one or more characteristics of different paths usable to transfer the data.
Inventor(s): Weili Nie of Sunnyvale CA (US) for nvidia corporation, Guan-Horng Liu of Marietta GA (US) for nvidia corporation, Arash Vahdat of San Mateo CA (US) for nvidia corporation, De-An Huang of Cupertino CA (US) for nvidia corporation, Anima Anandkumar of Pasadena CA (US) for nvidia corporation
IPC Code(s): G06T5/60, G06T5/50
CPC Code(s): G06T5/60
Abstract: image restoration generally involves recovering a target clean image from a given image having noise, blurring, or other degraded features. current image restoration solutions typically include a diffusion model that is trained for image restoration by a forward process that progressively diffuses data to noise, and then by learning in a reverse process to generate the data from the noise. however, the forward process relies on gaussian noise to diffuse the original data, which has little or no structural information corresponding to the original data versus learning from the degraded image itself which is much more structurally informative compared to the random gaussian noise. similar problems also exist for other data-to-data translation tasks. the present disclosure trains a data translation conditional diffusion model from diffusion bridge(s) computed between a first version of the data and a second version of the data, which can yield a model that can provide interpretable generation, sampling efficiency, and reduced processing time.
Inventor(s): Yue Wang of Mountain View CA (US) for nvidia corporation, Marco Pavone of Stanford CA (US) for nvidia corporation, Jiawei Yang of Los Angeles CA (US) for nvidia corporation
IPC Code(s): G06T15/00, G06T15/06
CPC Code(s): G06T15/005
Abstract: in various examples, frequency regularization and/or occlusion regularization techniques may be used to train neural radiance fields (nerf) to determine neural renderings based at least on sparse inputs in a way that reduces overfitting, underfitting, and/or occlusions. for example, while training a nerf, a linearly increased frequency mask may be applied to regularize a visible frequency spectrum of training data based on training time steps. in examples, as training of the nerf progresses, the visible frequency may be increased in a way that reduces the risk of overfitting and/or avoids underfitting. additionally, the disclosed techniques may also include masking one or more density scores located within a threshold proximity of an origin of a ray to reduce floaters, walls, and other occlusions in the neural rendering output.
Inventor(s): Ankit Goyal of Seattle WA (US) for nvidia corporation, Jie Xu of Bellevue WA (US) for nvidia corporation, Yijie Guo of Seattle WA (US) for nvidia corporation, Valts Blukis of Seattle WA (US) for nvidia corporation, Yu-Wei Chao of Redmond WA (US) for nvidia corporation, Dieter Fox of Seattle WA (US) for nvidia corporation
IPC Code(s): G06T15/10, G05D1/243, G05D101/15, G06T7/55
CPC Code(s): G06T15/10
Abstract: in various examples, a machine may generate, using sensor data capturing one or more views of an environment, a virtual environment including a 3d representation of the environment. the machine may render, using one or more virtual sensors in the virtual environment, one or more images of the 3d representation of the environment. the machine may apply the one or more images to one or more machine learning models (mlms) trained to generate one or more predictions corresponding to the environment. the machine may perform one or more control operations based at least on the one or more predictions generated using the one or more mlms.
Inventor(s): Nikolai Smolyanskiy of Seattle WA (US) for nvidia corporation, Ryan Oldja of Redmond WA (US) for nvidia corporation, Ke Chen of Sunnyvale CA (US) for nvidia corporation, Alexander Popov of Kirkland WA (US) for nvidia corporation, Joachim Pehserl of Lynnnwood WA (US) for nvidia corporation, Ibrahim Eden of Redmond WA (US) for nvidia corporation, Tilman Wekel of Sunnyvale CA (US) for nvidia corporation, David Wehr of Redmond WA (US) for nvidia corporation, Ruchi Bhargava of Redmond WA (US) for nvidia corporation, David Nister of Bellevue WA (US) for nvidia corporation
IPC Code(s): G06V20/58, B60W60/00, G01S17/89, G01S17/931, G06N3/045, G06T19/00
CPC Code(s): G06V20/584
Abstract: a deep neural network(s) (dnn) may be used to detect objects from sensor data of a three dimensional (3d) environment. for example, a multi-view perception dnn may include multiple constituent dnns or stages chained together that sequentially process different views of the 3d environment. an example dnn may include a first stage that performs class segmentation in a first view (e.g., perspective view) and a second stage that performs class segmentation and/or regresses instance geometry in a second view (e.g., top-down). the dnn outputs may be processed to generate 2d and/or 3d bounding boxes and class labels for detected objects in the 3d environment. as such, the techniques described herein may be used to detect and classify animate objects and/or parts of an environment, and these detections and classifications may be provided to an autonomous vehicle drive stack to enable safe planning and control of the autonomous vehicle.
Inventor(s): Kang Wang of Bellevue WA (US) for nvidia corporation, Yue Wu of Mountain View CA (US) for nvidia corporation, Minwoo Park of Saratoga CA (US) for nvidia corporation, Gang Pan of Fremont CA (US) for nvidia corporation
IPC Code(s): G06V20/64, B60G17/0165, B60K31/00, B60W60/00, G01S17/89, G01S17/931, G06F18/214, G06V20/58
CPC Code(s): G06V20/64
Abstract: in various examples, to support training a deep neural network (dnn) to predict a dense representation of a 3d surface structure of interest, a training dataset is generated from real-world data. for example, one or more vehicles may collect image data and lidar data while navigating through a real-world environment. to generate input training data, 3d surface structure estimation may be performed on captured image data to generate a sparse representation of a 3d surface structure of interest (e.g., a 3d road surface). to generate corresponding ground truth training data, captured lidar data may be smoothed, subject to outlier removal, subject to triangulation to filling missing values, accumulated from multiple lidar sensors, aligned with corresponding frames of image data, and/or annotated to identify 3d points on the 3d surface of interest, and the identified 3d points may be projected to generate a dense representation of the 3d surface structure.
20240274119. AUDIO SIGNAL GENERATION USING NEURAL NETWORKS_simplified_abstract_(nvidia corporation)
Inventor(s): Sudheer Kumar Kovela of Visakhapatnam (IN) for nvidia corporation, Ambrish Dantrey of Pune (IN) for nvidia corporation, José Rafael Valle Gomes da Costa of Berkeley CA (US) for nvidia corporation
IPC Code(s): G10L13/02, G10L25/30
CPC Code(s): G10L13/02
Abstract: apparatuses, systems, and techniques to generate audio signals. in at least one embodiment, features are identified in input audio signals using one or more neural networks which generate an output audio signal based on the identified features.
- NVIDIA Corporation
- G06F9/48
- G06F9/30
- G06F9/38
- G06F9/50
- G06F9/54
- G06F11/07
- G06F21/52
- CPC G06F9/4881
- Nvidia corporation
- G06F13/42
- CPC G06F9/5016
- CPC G06F9/5072
- G06F13/28
- G06F13/40
- G06F15/173
- CPC G06F13/4282
- G06T5/60
- G06T5/50
- CPC G06T5/60
- G06T15/00
- G06T15/06
- CPC G06T15/005
- G06T15/10
- G05D1/243
- G05D101/15
- G06T7/55
- CPC G06T15/10
- G06V20/58
- B60W60/00
- G01S17/89
- G01S17/931
- G06N3/045
- G06T19/00
- CPC G06V20/584
- G06V20/64
- B60G17/0165
- B60K31/00
- G06F18/214
- CPC G06V20/64
- G10L13/02
- G10L25/30
- CPC G10L13/02