Patents by Inventor Ajit Deepak Gupte
Ajit Deepak Gupte 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).
-
Patent number: 12236631Abstract: Systems and techniques are described herein for processing frames. The systems and techniques can be implemented by various types of systems, such as by an extended reality (XR) system or device. In some cases, a process can include obtaining feature information associated with a feature in a current frame, wherein the feature information is based on one or more previous frames; determining an estimated pose of the apparatus associated with the current frame; obtaining a distance associated with the feature in the current frame; and determining an estimated scale of the feature in the current frame based on the feature information associated with the feature, the estimated pose, and the distance associated with the feature.Type: GrantFiled: September 24, 2021Date of Patent: February 25, 2025Assignee: QUALCOMM IncorporatedInventors: Pushkar Gorur Sheshagiri, Ajit Deepak Gupte, Chiranjib Choudhuri, Gerhard Reitmayr, Youngmin Park
-
Patent number: 12219156Abstract: Several methods and systems for chroma residual data prediction for encoding blocks corresponding to video data are disclosed. In an embodiment, at least one coefficient correlating reconstructed luma residual samples and corresponding reconstructed chroma residual samples is computed for one or more encoded blocks of video data. Predicted chroma residual samples are generated for encoding a block of video data based on corresponding reconstructed luma residual samples and the at least one coefficient.Type: GrantFiled: April 21, 2022Date of Patent: February 4, 2025Assignee: TEXAS INSTRUMENTS INCORPORATEDInventors: Ajit Deepak Gupte, Ranga Ramanujam Srinivasan
-
Patent number: 12147519Abstract: Systems and techniques are provided for performing user authentication. For example, a process can include obtaining a plurality of images associated with a face and a facial expression of the user, wherein each respective image of the plurality of images includes a different portion of the face. An encoder neural network can be used to generate one or more predicted three-dimensional (3D) facial modeling parameters, wherein the encoder neural network generates the one or more predicted 3D facial modeling parameters based on the plurality of images. A reference 3D facial model associated with the face and the facial expression can be obtained. An error can be determined between the one or more predicted 3D facial modeling parameters and the reference 3D facial model, and the user can be authenticated user based on the error being less than a pre-determined authentication threshold.Type: GrantFiled: September 16, 2022Date of Patent: November 19, 2024Assignee: QUALCOMM IncorporatedInventors: Anupama S, Chiranjib Choudhuri, Avani Rao, Ajit Deepak Gupte
-
Patent number: 12056808Abstract: Methods, devices, and apparatuses are provided to facilitate a positioning of an item of virtual content in an extended reality environment. For example, a placement position for an item of virtual content can be transmitted to one or more of a first device and a second device. The placement position can be based on correlated map data generated based on first map data obtained from the first device and second map data obtained from the second device. In some examples, the first device can transmit the placement position to the second device.Type: GrantFiled: May 4, 2023Date of Patent: August 6, 2024Assignee: QUALCOMM IncorporatedInventors: Pushkar Gorur Sheshagiri, Pawan Kumar Baheti, Ajit Deepak Gupte, Sandeep Kanakapura Lakshmikantha
-
Publication number: 20240037700Abstract: The architecture shown can perform global search, local search and local sub pixel search in a parallel or in a pipelined mode. All operations are in a streaming mode without the requirement of external intermediate data storage.Type: ApplicationFiled: October 12, 2023Publication date: February 1, 2024Inventors: Mahesh M. Mehendale, Ajit Deepak Gupte
-
Patent number: 11790485Abstract: The architecture shown can perform global search, local search and local sub pixel search in a parallel or in a pipelined mode. All operations are in a streaming mode without the requirement of external intermediate data storage.Type: GrantFiled: August 25, 2021Date of Patent: October 17, 2023Assignee: Texas Instruments IncorporatedInventors: Mahesh M. Mehendale, Ajit Deepak Gupte
-
Patent number: 11769258Abstract: Systems and techniques are described herein for processing images. The systems and techniques can be implemented by various types of systems, such as by an extended reality (XR) system or device. In some cases, a first processor receives an image of an environment captured by an image sensor, identifies features depicted in the image, and generates descriptors for the features. The first processor sends the descriptors to a second processor, which may be more powerful than the first processor. The second processor receives the descriptors. The second processor associates the plurality of features with a map of the environment based on at least a subset of the plurality of descriptors. For example, the second processor can track at least a subset of the features based on at least a subset of the descriptors and based on feature information from one or more additional images of the environment.Type: GrantFiled: February 3, 2021Date of Patent: September 26, 2023Assignee: QUALCOMM IncorporatedInventors: Ajit Deepak Gupte, Gerhard Reitmayr, Abhijeet Bisain, Pushkar Gorur Sheshagiri, Chayan Sharma, Ajit Venkat Rao
-
Patent number: 11756227Abstract: Systems and techniques are provided for determining and applying corrected poses in digital content experiences. An example method can include receiving, from one or more sensors associated with an apparatus, inertial measurements and one or more frames of a scene; based on the one or more frames and the inertial measurements, determining, via a first filter, an angular and linear motion of the apparatus and a gravity vector indicating a direction of gravitational force interacting with the apparatus; when a motion of the apparatus is below a threshold, determining, via a second filter, an updated gravity vector indicating a direction of gravitational force interacting with the apparatus; determining, based on the updated gravity vector, parameters for aligning an axis of the scene with a gravity direction in a real-world spatial frame; and aligning, using the parameters, the axis of the scene with the gravity direction in the real-world spatial frame.Type: GrantFiled: May 4, 2021Date of Patent: September 12, 2023Assignee: QUALCOMM IncorporatedInventors: Srujan Babu Nandipati, Pushkar Gorur Sheshagiri, Chiranjib Choudhuri, Ajit Deepak Gupte, Gerhard Reitmayr
-
Patent number: 11727625Abstract: Methods, devices, and apparatuses are provided to facilitate a positioning of an item of virtual content in an extended reality environment. For example, a placement position for an item of virtual content can be transmitted to one or more of a first device and a second device. The placement position can be based on correlated map data generated based on first map data obtained from the first device and second map data obtained from the second device. In some examples, the first device can transmit the placement position to the second device.Type: GrantFiled: November 23, 2021Date of Patent: August 15, 2023Assignee: QUALCOMM IncorporatedInventors: Pushkar Gorur Sheshagiri, Pawan Kumar Baheti, Ajit Deepak Gupte, Sandeep Kanakapura Lakshmikantha
-
Publication number: 20220248037Abstract: Several methods and systems for chroma residual data prediction for encoding blocks corresponding to video data are disclosed. In an embodiment, at least one coefficient correlating reconstructed luma residual samples and corresponding reconstructed chroma residual samples is computed for one or more encoded blocks of video data. Predicted chroma residual samples are generated for encoding a block of video data based on corresponding reconstructed luma residual samples and the at least one coefficient.Type: ApplicationFiled: April 21, 2022Publication date: August 4, 2022Inventors: Ajit Deepak Gupte, Ranga Ramanujam Srinivasan
-
Patent number: 11323724Abstract: Several methods and systems for chroma residual data prediction for encoding blocks corresponding to video data are disclosed. In an embodiment, at least one coefficient correlating reconstructed luma residual samples and corresponding reconstructed chroma residual samples is computed for one or more encoded blocks of video data. Predicted chroma residual samples are generated for encoding a block of video data based on corresponding reconstructed luma residual samples and the at least one coefficient.Type: GrantFiled: September 15, 2020Date of Patent: May 3, 2022Assignee: TEXAS INSTRUMENTS INCORPORATEDInventors: Ajit Deepak Gupte, Ranga Ramanujam Srinivasan
-
Patent number: 11200729Abstract: Methods, devices, and apparatuses are provided to facilitate a positioning of an item of virtual content in an extended reality environment. For example, a placement position for an item of virtual content can be transmitted to one or more of a first device and a second device. The placement position can be based on correlated map data generated based on first map data obtained from the first device and second map data obtained from the second device. In some examples, the first device can transmit the placement position to the second device.Type: GrantFiled: September 24, 2020Date of Patent: December 14, 2021Assignee: QUALCOMM IncorporatedInventors: Pushkar Gorur Sheshagiri, Pawan Kumar Baheti, Ajit Deepak Gupte, Sandeep Kanakapura Lakshmikantha
-
Publication number: 20210383504Abstract: The architecture shown can perform global search, local search and local sub pixel search in a parallel or in a pipelined mode. All operations are in a streaming mode without the requirement of external intermediate data storage.Type: ApplicationFiled: August 25, 2021Publication date: December 9, 2021Inventors: Mahesh M. Mehendale, Ajit Deepak Gupte
-
Patent number: 11144117Abstract: Methods, systems, and devices for deep learning based head motion prediction for extended reality are described. The head pose prediction may involve training one or more layers of a machine learning network based on application data and an estimated head motion range associated with the extended reality system. The network may receive one or more bias corrected inertial measurement unit (IMU) measurements based on a sensor. The network may model a relative head pose of the user as a polynomial of time over a prediction interval based on the bias corrected IMU measurements and the trained one or more layers of the machine learning network. The network may determine a future relative head pose of the user based on the polynomial (e.g., which may be used for virtual object generation, display, etc. within an extended reality system).Type: GrantFiled: May 18, 2020Date of Patent: October 12, 2021Assignee: QUALCOMM IncorporatedInventors: Chiranjib Choudhuri, Ajit Deepak Gupte, Pushkar Gorur Sheshagiri, Gerhard Reitmayr, Tom Edward Botterill
-
Patent number: 11127114Abstract: The architecture shown can perform global search, local search and local sub pixel search in a parallel or in a pipelined mode. All operations are in a streaming mode without the requirement of external intermediate data storage.Type: GrantFiled: March 4, 2020Date of Patent: September 21, 2021Assignee: TEXAS INSTRUMENTS INCORPORATEDInventors: Mahesh M. Mehendale, Ajit Deepak Gupte
-
Patent number: 11010921Abstract: Systems, methods, and computer-readable media are provided for distributed tracking and mapping for extended reality experiences. An example method can include computing, at a device, a pose of the device at a future time, the future time being determined based on a communication latency between the device and a mapping backend system; sending, to the mapping backend system, the pose of the device; receiving, from the mapping backend system, a map slice including map points corresponding to a scene associated with the device, the map slice being generated based on the pose of the device, wherein the map points correspond to the predicted pose; and computing an updated pose of the device based on the map slice.Type: GrantFiled: May 16, 2019Date of Patent: May 18, 2021Assignee: QUALCOMM IncorporatedInventors: Chiranjib Choudhuri, Pushkar Gorur Sheshagiri, Ajit Deepak Gupte, Vinay Melkote Krishnaprasad, Chayan Sharma, Ajit Venkat Rao
-
Publication number: 20200413076Abstract: Several methods and systems for chroma residual data prediction for encoding blocks corresponding to video data are disclosed. In an embodiment, at least one coefficient correlating reconstructed luma residual samples and corresponding reconstructed chroma residual samples is computed for one or more encoded blocks of video data. Predicted chroma residual samples are generated for encoding a block of video data based on corresponding reconstructed luma residual samples and the at least one coefficient.Type: ApplicationFiled: September 15, 2020Publication date: December 31, 2020Inventors: Ajit Deepak Gupte, Ranga Ramanujam Srinivasan
-
Patent number: 10825237Abstract: Methods, devices, and apparatuses are provided to facilitate a positioning of an item of virtual content in an extended reality environment. For example, a first user may access the extended reality environment through a display of a mobile device, and in some examples, the methods may determine positions and orientations of the first user and a second user within the extended reality environment. The methods may also determine a position for placement of the item of virtual content in the extended reality environment based on the determined positions and orientations of the first user and the second user, and perform operations that insert the item of virtual content into the extended reality environment at the determined placement position.Type: GrantFiled: April 5, 2019Date of Patent: November 3, 2020Assignee: QUALCOMM IncorporatedInventors: Pushkar Gorur Sheshagiri, Pawan Kumar Baheti, Ajit Deepak Gupte, Sandeep Kanakapura Lakshmikantha
-
Patent number: 10805619Abstract: Several methods and systems for chroma residual data prediction for encoding blocks corresponding to video data are disclosed. In an embodiment, at least one coefficient correlating reconstructed luma residual samples and corresponding reconstructed chroma residual samples is computed for one or more encoded blocks of video data. Predicted chroma residual samples are generated for encoding a block of video data based on corresponding reconstructed luma residual samples and the at least one coefficient.Type: GrantFiled: April 16, 2018Date of Patent: October 13, 2020Assignee: TEXAS INSTRUMENTS INCORPORATEDInventors: Ajit Deepak Gupte, Ranga Ramanujam Srinivasan
-
Patent number: 10767997Abstract: Systems, methods, and computer-readable media are provided for immersive extended reality experiences on mobile platforms. In some examples, a method can include obtaining sensor measurements from one or more sensors on a mobile platform and/or a device associated with a user in the mobile platform, the sensor measurements including motion parameters associated with the mobile platform and the user; identifying features of the mobile platform and an environment outside of the mobile platform; tracking, using the sensor measurements, a first pose of the mobile platform relative to the environment outside of the mobile platform; tracking, using the sensor measurements, a second pose of the user relative to at least one of the features of the mobile platform; and tracking, based on the first pose and the second pose, a third pose of the user relative to at least one of the features of the environment outside of the mobile platform.Type: GrantFiled: February 25, 2019Date of Patent: September 8, 2020Assignee: QUALCOMM IncorporatedInventors: Pushkar Gorur Sheshagiri, Chayan Sharma, Chiranjib Choudhuri, Ajit Deepak Gupte