-
公开(公告)号：US12002127B2
公开(公告)日：2024-06-04
申请号：US16924849
申请日：2020-07-09
Applicant: SAMSUNG ELECTRONICS CO., LTD.
Inventor： Yoel Yaffe , Ariel Orfaig , Gershi Koltun , Amit Eisenberg , Ishay Goldin , Shai Litvak
CPC classification number: G06T1/0042 , G06T1/0028 , H04L9/3242 , G06T2201/0052 , G06T2201/0065
Abstract: A method for processing a digital content includes acquiring content data using a sensor. Compressed reference data is generated from the acquired content data. A hash of the compressed reference data is generated using a hashing function. The generated hash is signed using an encryption function. The acquired content data is transmitted along with the compressed reference data and the signed hash.
-
公开(公告)号：US20250046071A1
公开(公告)日：2025-02-06
申请号：US18755803
申请日：2024-06-27
Applicant: SAMSUNG ELECTRONICS CO., LTD.
Inventor： Ishay Goldin , Avraham Raviv , Yonatan Dinai , Nimrod Harel , Niv Zehngut
Abstract: Aspects of the method, apparatus, non-transitory computer readable medium, and system include obtaining a video comprising a plurality of video frames; computing, using a machine learning model, a global dependency value based on the plurality of video frames; deactivating a filter of the machine learning model based on the global dependency value; and processing, using the machine learning model, at least a portion of the video based on the deactivated filter.
-
Patent Agency Ranking
公开(公告)号：US20230377321A1
公开(公告)日：2023-11-23
申请号：US17664262
申请日：2022-05-20
Applicant: SAMSUNG ELECTRONICS CO., LTD.
Inventor： Ishay Goldin , Yonatan Dinai , Ran Vitek , Michael Dinerstein
Abstract: One or more aspects of the present disclosure enable high accuracy computer vision and image processing techniques with decreased system resource requirements (e.g., with decreased computational load, shallower neural network designs, etc.). As described in more detail herein, one or more aspects of the described techniques may leverage key layers (e.g., certain key layers of a neural network) and compressed tensor comparisons to efficiently exploit temporal redundancy in videos and other slow changing signals (e.g., to efficiently reduce neural network inference computational burden, with only minor increase in data transfer power consumption). For example, key layers of a neural network may be identified, and temporal/spatial redundancy across frames may be efficiently leveraged such that only a computation region in a subsequent frame n+1 is re-computed in layers between identified key layers, while remaining feature-map calculations may be disabled in the layers between the identified key layers.
-
公开(公告)号：US20250054117A1
公开(公告)日：2025-02-13
申请号：US18447743
申请日：2023-08-10
Applicant: SAMSUNG ELECTRONICS CO., LTD.
Inventor： Gil Shapira , Ishay Goldin , Niv Zehngut , David Tal
Abstract: Systems and methods for image processing (e.g., image correction) are described. Embodiments of the present disclosure include image processing techniques that reduce or remove Moiré patterns by leveraging low resolution images (e.g., images captured using low resolution sensors, such as an ultra-wide camera). For instance, an image including a Moiré pattern may be corrected based on a second image having a low resolution. In one example, a device may capture a high resolution image that includes a Moiré pattern. The device may also capture a low resolution image that is aligned with the high resolution image and used to correct (e.g., remove) the Moiré pattern. In some embodiments, the systems and techniques described herein may be implemented in real-time on a user device (e.g., that includes a high resolution image sensor and a low resolution image sensor) for efficient and effective correction of Moiré patterns in image/video capture applications.
-
公开(公告)号：US20230368520A1
公开(公告)日：2023-11-16
申请号：US17663035
申请日：2022-05-12
Applicant: SAMSUNG ELECTRONICS CO., LTD.
Inventor： Ishay Goldin , Netanel Stein , Alexandra Dana , Alon Intrater , David Tsidkiahu , Nathan Levy , Omer Shabtai , Ran Vitek , Tal Heller , Yaron Ukrainitz , Yotam Platner , Zuf Pilosof
CPC classification number: G06V10/96 , G06T3/4046 , G06V20/49 , G06V10/82 , G06V20/41 , G06V20/70 , G06V10/774
Abstract: Techniques and apparatuses enabling high accuracy video object detection using reduced system resource requirements (e.g., reduced computational load, shallower neural network designs, etc.) are described. For example, a search domain of an object detection scheme (e.g., a target object class, a target object size, a target object rotation angle, etc.) may be separated into subdomains (e.g., such as subdomains of object classes, subdomains of object sizes, subdomains object rotation angles, etc.). Specialized, subdomain-level object detection/segmentation tasks may then be separated across sequential video frames. As such, different subdomain-level processing techniques (e.g., via specialized neural networks) may be implemented across different frames of a video sequence. Moreover, redundancy information of consecutive video frames may be leveraged, such that specialized object detection tasks combined with visual object tracking across consecutive frames may enable more efficient (e.g., more accurate, less computationally intensive, etc.) full domain object detection and object segmentation schemes.
-
公开(公告)号：US11574500B2
公开(公告)日：2023-02-07
申请号：US17151339
申请日：2021-01-18
Applicant: SAMSUNG ELECTRONICS CO., LTD.
Inventor： Gil Shapira , Noga Levy , Roy Jevnisek , Ishay Goldin
Abstract: Embodiments of the present disclosure enable and accurate detection of facial landmarks on mobile devices in real-time. An architecture of a facial landmark detection model is provided including one or more of an attention mechanism (e.g., an attention network), a graph convolution model (e.g., a two-dimensional facial geometry graph convolution model), a multiscale coarse-to-fine mechanism, a patch-facial landmark detachment mechanism, and error estimation techniques. The attention mechanism may increase the accuracy of the facial landmark detection model by attending to meaningful patches. The graph convolution network may improve patch feature aggregation by considering the facial landmarks' geometry. The coarse-to-fine mechanism reduces a network convergence to two cycles (e.g., two facial landmark detection iterations). A patch-facial landmark detachment mechanism reduces the computation burden without significant accuracy degradation. Error estimation techniques provide accurate estimation of the regression error to the computation load and increase the accuracy of the model.
-
公开(公告)号：US20220075994A1
公开(公告)日：2022-03-10
申请号：US17151339
申请日：2021-01-18
Applicant: SAMSUNG ELECTRONICS CO., LTD.
Inventor： GIL SHAPIRA , Noga Levy , Roy Jevnisek , Ishay Goldin
Abstract: Embodiments of the present disclosure enable and accurate detection of facial landmarks on mobile devices in real-time. An architecture of a facial landmark detection model is provided including one or more of an attention mechanism (e.g., an attention network), a graph convolution model (e.g., a two-dimensional facial geometry graph convolution model), a multiscale coarse-to-fine mechanism, a patch-facial landmark detachment mechanism, and error estimation techniques. The attention mechanism may increase the accuracy of the facial landmark detection model by attending to meaningful patches. The graph convolution network may improve patch feature aggregation by considering the facial landmarks' geometry. The coarse-to-fine mechanism reduces a network convergence to two cycles (e.g., two facial landmark detection iterations). A patch-facial landmark detachment mechanism reduces the computation burden without significant accuracy degradation. Error estimation techniques provide accurate estimation of the regression error to the computation load and increase the accuracy of the model.
-
-
-
-
-
-
Search Results
7
records
(took 0.013 seconds)
