NVIDIA Corporation patent applications on August 8th, 2024
Patent Applications by NVIDIA Corporation on August 8th, 2024
NVIDIA Corporation: 18 patent applications
NVIDIA Corporation has applied for patents in the areas of G06F18/214 (3), G06V10/82 (3), G10L15/06 (2), G06N3/08 (2), G06N20/00 (2) G06T15/06 (2), G10L15/16 (2), B25J9/1689 (1), G05B19/41885 (1), G06F1/08 (1)
With keywords such as: shading, lens, correction, respective, frame, image, representation, data, scene, and systems in patent application abstracts.
Patent Applications by NVIDIA Corporation
20240261971. VISION BASED ROBOT TELEOPERATION_simplified_abstract_(nvidia corporation)
Inventor(s): Yuzhe Qin of San Diego CA (US) for nvidia corporation, Wei Yang of Lake Forest Park 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): B25J9/16, B25J19/02, G06T7/50, G06T7/70, G06V10/82, G06V40/10
CPC Code(s): B25J9/1689
Abstract: apparatuses, systems, and techniques to generate control commands. in at least one embodiment, control commands are generated based on, for example, one or more images depicting a hand.
20240264588. ARTIFICIAL-INTELLIGENCE-BASED MANUFACTURING_simplified_abstract_(nvidia corporation)
Inventor(s): Ron Chao of San Diego CA (US) for nvidia corporation, Liang-I Lin of Milpitas CA (US) for nvidia corporation, Tuan Ong of Santa Clara CA (US) for nvidia corporation, Elad Mentovich of Tel Aviv (IL) for nvidia corporation, Siddha Ganju of Santa Clara CA (US) for nvidia corporation, Dinesh Krishnaswamy of San Jose CA (US) for nvidia corporation, Fisher Liu of Shenzhen (CN) for nvidia corporation, Lei Huang of Shenzhen (CN) for nvidia corporation, Nicholas Girard Page of San Jose CA (US) for nvidia corporation
IPC Code(s): G05B19/418
CPC Code(s): G05B19/41885
Abstract: methods are described herein for artificial-intelligence-based manufacturing. the present invention may include performing an initial step in a series of steps to achieve a target value of an attribute, where the series of steps is for manufacturing an object, and, after performing the initial step, measuring an actual value of the attribute achieved by the initial step. the method may include, for each subsequent step in the series, providing actual values of attributes achieved by preceding steps in the series to a respective machine learning model to determine a respective target value for a respective attribute to be achieved by the respective step. the method may also include, for each step, performing the respective step to achieve the respective target value of the respective attribute and, after performing the respective step, measuring a respective actual value of the respective attribute achieved by the respective step.
Inventor(s): Jiale Liang of San Jose CA (US) for nvidia corporation, Tezaswi Raja of San Jose CA (US) for nvidia corporation, Suhas Satheesh of Sunnyvale CA (US) for nvidia corporation, Shalimar Rasheed of San Jose CA (US) for nvidia corporation, Gaurav Ajwani of Union City CA (US) for nvidia corporation, Ram Kumar Ranjith Kumar of Brantford (CA) for nvidia corporation, Miloni Mehta of San Jose CA (US) for nvidia corporation
IPC Code(s): G06F1/08, H03K5/01
CPC Code(s): G06F1/08
Abstract: circuits that include one or more transmission lines to propagate a signal through a serially-arranged plurality of repeaters, and one or more control circuits to propagate control pulses to the repeaters, wherein a timing and duration of the control pulses is configured to operate the repeaters in current-mode signaling (cms) mode during a state transition of the signal at the repeaters and to operate the repeaters in voltage-mode signaling (vms) mode otherwise.
Inventor(s): Michael Murphy of Newark CA (US) for nvidia corporation, Shelton George Dsouza of San Jose CA (US) for nvidia corporation, Shandeep Nagori of Pune (IN) for nvidia corporation, Thibaut Lutz of Kirkland WA (US) for nvidia corporation
IPC Code(s): G06F9/455, G06F9/445
CPC Code(s): G06F9/4552
Abstract: a first intermediate representation of a first portion of a source code implementing an application and a second intermediate representation of a second portion of the source code is received by a processing device. the first intermediate representation and the second intermediate representation is merged, at run-time, into a merged intermediate representation, wherein the first intermediate representation includes a reference to a function in the second intermediate representation. an execution flow transfer instruction within the merged intermediate representation is identified based on a run-time value of a parameter of the application. the execution flow transfer instruction references the function. a set of executable instructions implementing the function is identified within the merged intermediate representation. the execution flow transfer instruction is replaced with a copy of the set of executable instructions implementing the function.
Inventor(s): Nuri Murat Arar of Zurich (CH) for nvidia corporation, Niranjan Avadhanam of Saratoga CA (US) for nvidia corporation, Nishant Puri of San Francisco CA (US) for nvidia corporation, Shagan Sah of Santa Clara CA (US) for nvidia corporation, Rajath Shetty of Santa Clara CA (US) for nvidia corporation, Sujay Yadawadkar of Santa Clara CA (US) for nvidia corporation, Pavlo Molchanov of Mountain View CA (US) for nvidia corporation
IPC Code(s): G06N3/08, G06F18/21, G06F18/214, G06N20/00, G06V10/764, G06V10/774, G06V10/82, G06V10/94, G06V20/59, G06V20/64, G06V40/16, G06V40/18
CPC Code(s): G06N3/08
Abstract: systems and methods for more accurate and robust determination of subject characteristics from an image of the subject. one or more machine learning models receive as input an image of a subject, and output both facial landmarks and associated confidence values. confidence values represent the degrees to which portions of the subject's face corresponding to those landmarks are occluded, i.e., the amount of uncertainty in the position of each landmark location. these landmark points and their associated confidence values, and/or associated information, may then be input to another set of one or more machine learning models which may output any facial analysis quantity or quantities, such as the subject's gaze direction, head pose, drowsiness state, cognitive load, or distraction state.
Inventor(s): Dong Zhang of Clarksville TN (US) for nvidia corporation, Sangmin Oh of San Jose CA (US) for nvidia corporation, Junghyun Kwon of Santa Clara CA (US) for nvidia corporation, Baris Evrim Demiroz of San Jose CA (US) for nvidia corporation, Tae Eun Choe of Belmont CA (US) for nvidia corporation, Minwoo Park of Saratoga CA (US) for nvidia corporation, Chethan Ningaraju of Munich (DE) for nvidia corporation, Hao Tsui of Munich (DE) for nvidia corporation, Eric Viscito of Shelburne VT (US) for nvidia corporation, Jagadeesh Sankaran of Dublin CA (US) for nvidia corporation, Yongqing Liang of San Jose CA (US) for nvidia corporation
IPC Code(s): G06T7/246, B60W60/00, G06F18/214, G06N3/08, G06V10/25, G06V10/75, G06V20/56, G06V20/58
CPC Code(s): G06T7/246
Abstract: systems and methods are disclosed that use a geometric approach to detect objects on a road surface. a set of points within a region of interest between a first frame and a second frame are captured and tracked to determine a difference in location between the set of points in two frames. the first frame may be aligned with the second frame and the first pixel values of the first frame may be compared with the second pixel values of the second frame to generate a disparity image including third pixels. subsets of the third pixels that have an disparity image value about a first threshold may be combined, and the third pixels may be scored and associated with disparity values for each pixel of the one or more subsets of the third pixels. a bounding shape may be generated based on the scoring that corresponds to the object.
20240265561. MESH RECONSTRUCTION USING DATA-DRIVEN PRIORS_simplified_abstract_(nvidia corporation)
Inventor(s): Orazio Gallo of Santa Cruz CA (US) for nvidia corporation, Abhishek Badki of Goleta CA (US) for nvidia corporation
IPC Code(s): G06T7/55, G06F17/16, G06F18/214, G06N20/00, G06T15/10, G06T17/20
CPC Code(s): G06T7/55
Abstract: one embodiment of a method includes predicting one or more three-dimensional (3d) mesh representations based on a plurality of digital images, wherein the one or more 3d mesh representations are refined by minimizing at least one difference between the one or more 3d mesh representations and the plurality of digital images.
20240265575. SHADING CALIBRATION FOR RADIAL SENSOR LENSES_simplified_abstract_(nvidia corporation)
Inventor(s): Yongshen NI of San Jose CA (US) for nvidia corporation, Eric Dujardin of San Jose CA (US) for nvidia corporation
IPC Code(s): G06T7/80, H04N17/00, H04N25/61
CPC Code(s): G06T7/80
Abstract: in various examples, systems and methods for calibration for sensor lens shading using non-radial correction of residual radial shading error are provided. in some embodiments, a calibration flow includes computation of calibration parameters corresponding to radial lens shading correction, and computation of calibration parameters corresponding to non-radial lens shading correction. a lens shading profile may be computed that defines a gain mapping of lens shading effect appearing in an image frame of calibration sensor data. parameters for radial lens shading correction may be computed from the lens shading profile, and parameters for non-radial lens shading correction may be computed based a residual shading profile generated from the radial lens shading correction. calibration parameters for radial and non-radial lens shading correction may be used to calibrate sensor data captured by an image sensor module to correct for lens shading.
20240265619. LEARNING DIGITAL TWINS OF RADIO ENVIRONMENTS_simplified_abstract_(nvidia corporation)
Inventor(s): Faycal Ait Aoudia of Santa Clara CA (US) for nvidia corporation, Jakob Richard Hoydis of Courbevoie (FR) for nvidia corporation, Nikolaus Binder of Berin (DE) for nvidia corporation, Merlin Nimier-David of Zürich (CH) for nvidia corporation, Sebastian Cammerer of Berliin (DE) for nvidia corporation, Alexander Georg Keller of Berlin (DE) for nvidia corporation, Guillermo Anibal Marcus Martinez of Berlin (DE) for nvidia corporation
IPC Code(s): G06T15/06, G06F30/27, G06N3/04
CPC Code(s): G06T15/06
Abstract: embodiments of the present disclosure relate to learning digital twins of radio environments. differentiable ray tracing may be used to refine the scene geometry of the physical environment, to learn or optimize the scene properties of objects in the scene, to learn or optimize the scene properties of antennas, and to learn or optimize antenna patterns, array geometries, and orientations and positions of transmitters and receivers. once scene properties have been learned or optimized, the differentiable ray tracer may further be used to simulate radio wave propagation to simulate the performance of different configurations of the scene geometry and radio devices, such as antennas. in an embodiment, one or more of the scene geometry, scene properties, and antenna characteristics are computed by a differentiable parametric function, such as a neural network, etc. and parameters of the differentiable parametric function are learned using the differentiable ray tracing.
Inventor(s): Jacopo Pantaleoni of Berlin (DE) for nvidia corporation
IPC Code(s): G06T15/06, G06T15/50
CPC Code(s): G06T15/06
Abstract: disclosed approaches provide for interactions of secondary rays of light transport paths in a virtual environment to share lighting contributions when determining lighting conditions for a light transport path. interactions may be shared based on similarities in characteristics (e.g., hit locations), which may define a region in which interactions may share lighting condition data. the region may correspond to a texel of a texture map and lighting contribution data for interactions may be accumulated to the texel spatially and/or temporally, then used to compute composite lighting contribution data that estimates radiance at an interaction. approaches are also provided for reprojecting lighting contributions of interactions to pixels to share lighting contribution data from secondary bounces of light transport paths while avoiding potential over blurring.
Inventor(s): Animashree Anandkumar of Pasadena CA (US) for nvidia corporation, Linxi Fan of Santa Clara CA (US) for nvidia corporation, Zhiding Yu of Santa Clara CA (US) for nvidia corporation, Chaowei Xiao of Tempe AZ (US) for nvidia corporation, Shikun Liu of London (GB) for nvidia corporation
IPC Code(s): G06V10/82, G06V10/80
CPC Code(s): G06V10/82
Abstract: a vision-language model learns skills and domain knowledge via distinct and separate task-specific neural networks, referred to as experts. each expert is independently optimized for a specific task, facilitating the use of domain-specific data and architectures that are not feasible with a single large neural network trained for multiple tasks. the vision-language model implemented as an ensemble of pre-trained experts and is more efficiently trained compared with the single large neural network. during training, the vision-language model integrates specialized skills and domain knowledge, rather than trying to simultaneously learn multiple tasks, resulting in effective multi-modal learning.
Inventor(s): David Wehr of Redmond WA (US) for nvidia corporation, Ibrahim Eden of Redmond WA (US) for nvidia corporation, Joachim Pehserl of Lynnwood WA (US) for nvidia corporation
IPC Code(s): G06V20/58, G01B11/22, G01S17/89, G05D1/249, G06N7/01, G06T7/579, G06T7/70
CPC Code(s): G06V20/58
Abstract: in various examples, systems and methods are described that generate scene flow in 3d space through simplifying the 3d lidar data to “2.5d” optical flow space (e.g., x, y, and depth flow). for example, lidar range images may be used to generate 2.5d representations of depth flow information between frames of lidar data, and two or more range images may be compared to generate depth flow information, and messages may be passed—e.g., using a belief propagation algorithm—to update pixel values in the 2.5d representation. the resulting images may then be used to generate 2.5d motion vectors, and the 2.5d motion vectors may be converted back to 3d space to generate a 3d scene flow representation of an environment around an autonomous machine.
Inventor(s): Aleksandr Laptev of Yerevan (AM) for nvidia corporation, Vladimir Bataev of Yerevan (AM) for nvidia corporation, Igor Gitman of Redmond WA (US) for nvidia corporation, Boris Ginsburg of Sunnyvale CA (US) for nvidia corporation
IPC Code(s): G10L15/16, G10L15/06
CPC Code(s): G10L15/16
Abstract: systems and methods provide for a machine learning system to train a machine learning model to output a penalty-free emission when processing an auditory input. for example, as the system generates paths through a probability lattice, one or more paths may include a penalty-free emission that skips at least one frame associated with the probability lattice, but that does not add a cost to a final path cost. the use of the penalty-free emissions may be represented through one or more graphical representations used for training in order to develop loss functions for models. one or more of these frameworks may be incorporated into automatic speech recognition pipelines to improve training while also reducing coding requirements to simplify debugging operations.
Inventor(s): Aleksandr Laptev of Yerevan (AM) for nvidia corporation, Vladimir Bataev of Yerevan (AM) for nvidia corporation, Igor Gitman of Redmond WA (US) for nvidia corporation, Boris Ginsburg of Sunnyvale CA (US) for nvidia corporation
IPC Code(s): G10L15/16, G10L15/06
CPC Code(s): G10L15/16
Abstract: systems and methods provide for a machine learning system to train a machine learning model to output a penalty-free emission when processing an auditory input. for example, as the system generates paths through a probability lattice, one or more paths may include a penalty-free emission that skips at least one frame associated with the probability lattice, but that does not add a cost to a final path cost. the use of the penalty-free emissions may be represented through one or more graphical representations used for training in order to develop loss functions for models. one or more of these frameworks may be incorporated into automatic speech recognition pipelines to improve training while also reducing coding requirements to simplify debugging operations.
Inventor(s): Joseph Minacapelli of Sunnyvale CA (US) for nvidia corporation, Cong Gao of Pflugerville TX (US) for nvidia corporation
IPC Code(s): H01F27/30
CPC Code(s): H01F27/306
Abstract: integrated inductors are formed by arranging multiple vias to bracket a volume of semiconductor substrate, where each via includes a top metal pad and a bottom metal pad. the vias are alternately connected by way of the top and bottom pads to form an end-to-end current loop along a length of the volume of semiconductor substrate.
Inventor(s): Jianjun Chen of Shanghai (CN) for nvidia corporation, Junan Chen of Nanjing (CN) for nvidia corporation, Yonghai Wu of Shanghai (CN) for nvidia corporation, Yongmao Tang of Shanghai (CN) for nvidia corporation, Xinan Lu of Shanghai (CN) for nvidia corporation
IPC Code(s): H04N19/14, H04N19/105, H04N19/176, H04N19/18
CPC Code(s): H04N19/14
Abstract: disclosed are apparatuses, systems, and techniques for efficient real-time codec encoding of video files. in one embodiment, the techniques include generating a block of predicted pixels that approximates a block of source pixels of an image frame and representing a difference between the block of source pixels and the block of predicted pixels via a plurality of transformation coefficients (tcs). the techniques further include evaluating tcs using statistical data for neighborhoods of the tcs to select an action for a respective tc, including adjusting the respective tc or maintaining the respective tc.
20240267647. LENS SHADING USING NON-RADIAL IMAGE CORRECTION_simplified_abstract_(nvidia corporation)
Inventor(s): Yongshen Ni of San Jose CA (US) for nvidia corporation, Eric Dujardin of San Jose CA (US) for nvidia corporation
IPC Code(s): H04N25/615
CPC Code(s): H04N25/615
Abstract: in various examples, lens shading image correction systems and applications using non-radial correction of residual radial shading error are provided. in some embodiments, lens shading image correction may be implemented using calibration parameters corresponding to radial lens shading correction, and calibration parameters corresponding to non-radial lens shading correction. in some embodiments, sensor data comprising an image frame may be captured using a sensor. radial lens shading correction may be applied to the image frame to produce a residual shading profile, and non-radial lens shading correction may be applied to the residual shading profile to produce a calibrated image frame. parameters for radial lens shading correction may be computed from a lens shading profile associated with the sensor, and parameters for non-radial lens shading correction may be computed based a residual shading profile produced from the radial lens shading correction.
Inventor(s): Ali Heydari of Albany CA (US) for nvidia corporation
IPC Code(s): H05K7/20, F28F13/00, F28F27/00
CPC Code(s): H05K7/20836
Abstract: systems and methods for cooling a datacenter are disclosed. in at least one embodiment, fins are provided within a cold plate and are adjustable to control an amount of surface area of the fins to be exposed to a fluid and to be cooled by the fluid based, at least in part, upon a temperature associated with the fluid or with at least one computing device.
- NVIDIA Corporation
- B25J9/16
- B25J19/02
- G06T7/50
- G06T7/70
- G06V10/82
- G06V40/10
- CPC B25J9/1689
- Nvidia corporation
- G05B19/418
- CPC G05B19/41885
- G06F1/08
- H03K5/01
- CPC G06F1/08
- G06F9/455
- G06F9/445
- CPC G06F9/4552
- G06N3/08
- G06F18/21
- G06F18/214
- G06N20/00
- G06V10/764
- G06V10/774
- G06V10/94
- G06V20/59
- G06V20/64
- G06V40/16
- G06V40/18
- CPC G06N3/08
- G06T7/246
- B60W60/00
- G06V10/25
- G06V10/75
- G06V20/56
- G06V20/58
- CPC G06T7/246
- G06T7/55
- G06F17/16
- G06T15/10
- G06T17/20
- CPC G06T7/55
- G06T7/80
- H04N17/00
- H04N25/61
- CPC G06T7/80
- G06T15/06
- G06F30/27
- G06N3/04
- CPC G06T15/06
- G06T15/50
- G06V10/80
- CPC G06V10/82
- G01B11/22
- G01S17/89
- G05D1/249
- G06N7/01
- G06T7/579
- CPC G06V20/58
- G10L15/16
- G10L15/06
- CPC G10L15/16
- H01F27/30
- CPC H01F27/306
- H04N19/14
- H04N19/105
- H04N19/176
- H04N19/18
- CPC H04N19/14
- H04N25/615
- CPC H04N25/615
- H05K7/20
- F28F13/00
- F28F27/00
- CPC H05K7/20836
