-
公开(公告)号：US20230377096A1
公开(公告)日：2023-11-23
申请号：US17746769
申请日：2022-05-17
Applicant: QUALCOMM Incorporated
Inventor： Yuri DOLGIN , Maksym ASLIANSKYI , Costia PARFENYEV , Eran PINHASOV , Victor PINTO
CPC classification number: G06T5/002 , G06T3/40 , G06T2207/10016 , G06T2207/20182 , G06T2207/20081
Abstract: The present disclosure generally relates to image processing. For example, aspects of the present disclosure include systems and techniques for performing spatial and temporal processing of image data. Certain aspects provide an apparatus for processing frame data. The apparatus generally includes a memory, and one or more processors coupled to the memory, the one or more processors configured to: perform a first noise reduction operation based on first frame data via a machine learning component to generate first processed frame data; generate first feedback data based on the first processed frame data; and perform, via the machine learning component, a second noise reduction operation based on second frame data and the first feedback data.
-
公开(公告)号：US20220060619A1
公开(公告)日：2022-02-24
申请号：US17158917
申请日：2021-01-26
Applicant: QUALCOMM Incorporated
Inventor： Eran PINHASOV , Scott CHENG , Eran SCHARAM , Anatoly GUREVICH
Abstract: Examples are described for applying different settings for image capture to different portions of image data. For example, an image sensor can capture image data of a scene and can send the image data to an image signal processor (ISP) and a classification engine for processing. The classification engine can determine that a first object image region depicts a first category of object, and a second object image region depicts a second category of object. Different confidence regions of the image data can identify different degrees of confidence in the classifications. The ISP can generate an image by applying a different settings to the different portions of the image data. The different portions of the image data can be identified based on the object image regions and confidence regions.
-
公开(公告)号：US20250095283A1
公开(公告)日：2025-03-20
申请号：US18468622
申请日：2023-09-15
Applicant: QUALCOMM Incorporated
Inventor： Eran PINHASOV , Eran SCHARAM
Abstract: Systems and techniques are provided for processing image data. A process can include determining an estimated camera pose corresponding to image data and generating a background replacement view of a configured three-dimensional (3D) content. The background replacement view can be associated with an angle-of-view (AOV) based on the estimated camera pose. A segmentation mask can be determined for the image data, indicative of a foreground portion of the image data and a background portion of the image data. A relighting image can be generated corresponding to at least a portion of the image data, wherein the relighting image is based on the segmentation mask and lighting information of the configured 3D content. An output image can be generated based on the relighting image and the background replacement view of the configured 3D content.
-
Patent Agency Ranking
公开(公告)号：US20240273858A1
公开(公告)日：2024-08-15
申请号：US18451347
申请日：2023-08-17
Applicant: QUALCOMM Incorporated
Inventor： Mark GINTSBURG , Eran PINHASOV
CPC classification number: G06V10/56 , G06T7/90 , G06V10/25 , G06V10/60 , H04N1/60 , G06T2207/10024 , G06T2207/30201
Abstract: Imaging systems and techniques are described. In some examples, an imaging system receives an image captured by an image sensor. The imaging system determines that an image region in the image includes a representation of an object of a specified category. The imaging system adjusts a hue (and/or saturation and/or brightness) of at least one pixel of the representation of the object in the image region to a specified hue (and/or saturation and/or brightness) to generate a processed image.
-
公开(公告)号：US20200077023A1
公开(公告)日：2020-03-05
申请号：US16120037
申请日：2018-08-31
Applicant: QUALCOMM Incorporated
Inventor： Young Hoon KANG , Hee Jun PARK , Tauseef KAZI , Ron GAIZMAN , Eran PINHASOV , Meir TZUR
Abstract: Techniques and systems are provided for machine-learning based image stabilization. In some examples, a system obtains a sequence of frames captured by an image capture device during a period of time, and collects motion sensor measurements calculated by a motion sensor associated with the image capture device based on movement of the image capture device during the period of time. The system generates, using a deep learning network and the motion sensor measurements, parameters for counteracting motions in one or more frames in the sequence of frames, the motions resulting from the movement of the image capture device during the period of time. The system then adjusts the one or more frames in the sequence of frames according to the parameters to generate one or more adjusted frames having a reduction in at least some of the motions in the one or more frames.
-
公开(公告)号：US20240121521A1
公开(公告)日：2024-04-11
申请号：US18545799
申请日：2023-12-19
Applicant: QUALCOMM Incorporated
Inventor： Eran PINHASOV , Scott CHENG , Eran SCHARAM , Anatoly GUREVICH
CPC classification number: H04N23/80 , G06V10/10 , G06V20/10 , G06V20/35 , H04N1/6072 , H04N1/6083 , H04N23/61 , H04N23/66 , H04N23/70 , H04N2101/00
Abstract: Examples are described for applying different settings for image capture to different portions of image data. For example, an image sensor can capture image data of a scene and can send the image data to an image signal processor (ISP) and a classification engine for processing. The classification engine can determine that a first object image region depicts a first category of object, and a second object image region depicts a second category of object. Different confidence regions of the image data can identify different degrees of confidence in the classifications. The ISP can generate an image by applying a different settings to the different portions of the image data. The different portions of the image data can be identified based on the object image regions and confidence regions.
-
公开(公告)号：US20220138964A1
公开(公告)日：2022-05-05
申请号：US17240837
申请日：2021-04-26
Applicant: QUALCOMM Incorporated
Inventor： Mark GINTSBURG , Nir STRAUSS , Ron GAIZMAN , Eran PINHASOV , Yuri DOLGIN , Victor PINTO
Abstract: Techniques and systems are provided for processing one or more frames or images. For instance, a process for determining exposure for one or more frames includes obtaining a motion map for one or more frames. The process includes determining, based on the motion map, motion associated with the one or more frames of a scene. The motion corresponds to movement of one or more objects in the scene relative to a camera used to capture the one or more frames. The process includes determining, based on the determined motion, a number of frames and an exposure for capturing the number of frames. The process further includes sending a request to capture the number of frames using the determined exposure duration.
-
公开(公告)号：US20200382706A1
公开(公告)日：2020-12-03
申请号：US16995546
申请日：2020-08-17
Applicant: QUALCOMM Incorporated
Inventor： Young Hoon KANG , Hee Jun PARK , Tauseef KAZI , Ron GAIZMAN , Eran PINHASOV , Meir TZUR
Abstract: Techniques and systems are provided for machine-learning based image stabilization. In some examples, a system obtains a sequence of frames captured by an image capture device during a period of time, and collects motion sensor measurements calculated by a motion sensor associated with the image capture device based on movement of the image capture device during the period of time. The system generates, using a deep learning network and the motion sensor measurements, parameters for counteracting motions in one or more frames in the sequence of frames, the motions resulting from the movement of the image capture device during the period of time. The system then adjusts the one or more frames in the sequence of frames according to the parameters to generate one or more adjusted frames having a reduction in at least some of the motions in the one or more frames.
-
-
-
-
-
-
-
Search Results
8
records
(took 0.016 seconds)
